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

    Neuronpedia

    INDEX
    Explanations

    disclaimers and statements of non-responsibility

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

    nor OR no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.58
    ScopeManager
    -0.52
    parsedMessage
    -0.49
     jspb
    -0.48
    FontOfSize
    -0.48
     GenerationType
    -0.48
     odkazy
    -0.48
     fieldNum
    -0.48
    UnusedPrivate
    -0.48
    __':
    -0.47
    POSITIVE LOGITS
     habet
    0.45
     traseiro
    0.38
     perſ
    0.36
    RefNanny
    0.36
    AndEndTag
    0.34
     perſon
    0.34
    Erstellt
    0.34
    inguém
    0.33
    运转
    0.33
    Sieg
    0.33
    Act Density 0.007%

    No Known Activations