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

    Neuronpedia

    INDEX
    Explanations

    scams and fraud

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rou
    -0.07
    險
    -0.07
    []}
    -0.07
    YSIS
    -0.06
    ;}
    -0.06
    sty
    -0.06
    observ
    -0.06
    (Stack
    -0.06
     town
    -0.06
    pción
    -0.06
    POSITIVE LOGITS
    ..<
    0.07
    EventType
    0.07
    攻撃
    0.06
    اذ
    0.06
    .ID
    0.06
     لي
    0.06
    forgettable
    0.06
    กำล
    0.06
    .SP
    0.06
    ंदर
    0.06
    Act Density 0.160%

    No Known Activations