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

    Neuronpedia

    INDEX
    Explanations

    expressions of capability or potential actions

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

    what can be done

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IVEREF
    -0.59
    rungsseite
    -0.54
    findpost
    -0.46
    EndGlobalSection
    -0.46
     ModelExpression
    -0.45
     typelib
    -0.43
     nahilalakip
    -0.42
     poveznice
    -0.41
    CUSSION
    -0.40
    expandindo
    -0.40
    POSITIVE LOGITS
    Хро
    0.45
    没办法
    0.41
    jší
    0.41
    无奈
    0.41
     helplessly
    0.39
    奈何
    0.39
    oneofs
    0.39
    Pax
    0.38
     Mercier
    0.38
    ห
    0.37
    Act Density 0.061%

    No Known Activations