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

    Neuronpedia

    INDEX
    Explanations

    expressions related to expectations or outcomes

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

    working as expected or intended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.30
    eseorang
    -0.30
    Autoritní
    -0.29
     circulación
    -0.29
    <%=
    -0.28
     quelqu
    -0.28
    })->
    -0.28
    Beginning
    -0.27
    Besides
    -0.27
    viene
    -0.27
    POSITIVE LOGITS
    featureID
    0.66
     EconPapers
    0.66
    QMetaType
    0.61
     autorytatywna
    0.61
     صوتيه
    0.60
     Италијани
    0.59
    EndInit
    0.58
     ProtoMessage
    0.58
     useAppContext
    0.58
    MessageWindow
    0.58
    Act Density 0.014%

    No Known Activations