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

    Neuronpedia

    INDEX
    Explanations

    phrases related to official statements or testimonies

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

    reporting speech and quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -0.65
    TypedDataSet
    -0.63
    Personensuche
    -0.62
     ujednoznacz
    -0.59
    󠁮
    -0.58
     snippetHide
    -0.57
    المناصب
    -0.56
     мәкал
    -0.56
    IsContent
    -0.54
     يتيمه
    -0.53
    POSITIVE LOGITS
    DispatchToProps
    0.36
     ebenfalls
    0.30
     Zacks
    0.29
     geldig
    0.29
     genoux
    0.28
     Erwachsenen
    0.28
    exitRule
    0.28
    ramanian
    0.27
    フォーマンス
    0.27
    pieler
    0.27
    Act Density 0.021%

    No Known Activations