Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that convey significance or essential information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the vital role

    np_acts-logits-general · gemini-2.5-flash-lite

    Sentences or phrases that introduce, define, or question a term (words like "term", "called", "widely recognized", quote marks and other definitional/meta-linguistic language).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.48
    gamon
    -0.47
    AutoField
    -0.47
    complexContent
    -0.45
    postmedia
    -0.44
    ModelAdmin
    -0.44
    ocarp
    -0.43
    +};
    -0.42
    Coil
    -0.42
    WebControls
    -0.42
    POSITIVE LOGITS
    webElementGuid
    0.51
     estekak
    0.48
    hilangan
    0.45
    gebung
    0.44
     terciopelo
    0.41
     CanadaChoose
    0.41
     Leinwand
    0.38
     Tropfen
    0.38
     bezeichneter
    0.37
     casquette
    0.37
    Act Density 2.584%

    No Known Activations