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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or terminology related to functions and mappings

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

    parameter maps obtained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.67
     שוליים
    -0.64
     EconPapers
    -0.58
     beginnetje
    -0.57
    NewUrlParser
    -0.56
     snippetHide
    -0.54
    évaluateur
    -0.54
    ьажоргаш
    -0.51
    SOUNDBITE
    -0.50
    StoryboardSegue
    -0.50
    POSITIVE LOGITS
     ModelRenderer
    0.42
    oredCriteria
    0.37
     équ
    0.36
    ustimmung
    0.36
     bílá
    0.35
     Einführung
    0.35
     valuta
    0.35
    WebElementEntity
    0.34
     MutableLiveData
    0.33
    inSlope
    0.33
    Act Density 0.427%

    No Known Activations