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

    Neuronpedia

    INDEX
    Explanations

    proper nouns associated with film and acting

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

    Tyson, Scorsese, dataclass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quieras
    -0.36
    DebuggerStep
    -0.32
     daya
    -0.31
     respeito
    -0.29
     preocu
    -0.29
     podamos
    -0.28
     inf
    -0.28
     vapeur
    -0.28
    Contenu
    -0.28
     dítě
    -0.27
    POSITIVE LOGITS
    principalColumn
    0.99
    Tyson
    0.89
     Tyson
    0.83
    celotti
    0.83
     виправивши
    0.82
    avut
    0.78
    dataclass
    0.77
    RTLR
    0.73
    Gambas
    0.70
    ghton
    0.66
    Act Density 0.012%

    No Known Activations