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

    Neuronpedia

    INDEX
    Explanations

    instances of reported speech and statements

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

    attributed statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.39
    ↵↵
    -0.32
    amboo
    -0.31
     the
    -0.31
    The
    -0.31
    운
    -0.30
    -
    -0.29
     Super
    -0.28
     pen
    -0.27
    Super
    -0.26
    POSITIVE LOGITS
     nahilalakip
    0.98
     AssemblyCulture
    0.90
    InjectAttribute
    0.86
     فريبيس
    0.85
     HasFactory
    0.85
     viewDidLoad
    0.82
    Hentet
    0.82
    ագրություններ
    0.81
    enumii
    0.80
    Personensuche
    0.79
    Act Density 0.022%

    No Known Activations