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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a perspective or viewpoint

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

    point of view

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.57
    principalColumn
    -0.57
    awtextra
    -0.54
    帖最后由
    -0.46
    rungsseite
    -0.46
    enumi
    -0.45
    Parcelize
    -0.45
     برانيه
    -0.44
    AnchorStyles
    -0.44
    matchCondition
    -0.42
    POSITIVE LOGITS
     ACCORD
    0.45
     AppCompat
    0.45
    AppMethodBeat
    0.44
    Tikang
    0.44
    palla
    0.43
    hamdu
    0.43
     treno
    0.43
     witness
    0.42
     FLU
    0.42
     Fung
    0.41
    Act Density 0.024%

    No Known Activations