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

    Neuronpedia

    INDEX
    Explanations

    Film ratings/censorship

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Royale
    -0.07
    DITION
    -0.06
    output
    -0.06
    :a
    -0.06
    руг
    -0.06
     output
    -0.06
    かな
    -0.06
     واقع
    -0.06
     قائمة
    -0.06
     towers
    -0.06
    POSITIVE LOGITS
     incontr
    0.07
     oracle
    0.06
     premature
    0.06
     buys
    0.06
     назад
    0.06
    /pay
    0.06
    "label
    0.06
     Incontri
    0.06
    _DD
    0.06
     Melee
    0.06
    Act Density 0.013%

    No Known Activations