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

    Neuronpedia

    INDEX
    Explanations

    negative outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SUS
    -0.06
    _shutdown
    -0.06
    906
    -0.06
    Sampler
    -0.06
    validator
    -0.06
    _nr
    -0.06
    .square
    -0.06
     spacing
    -0.06
    REAT
    -0.06
    Size
    -0.06
    POSITIVE LOGITS
     تنظ
    0.07
    Impro
    0.07
    IBUTES
    0.06
    اختی
    0.06
     kicked
    0.06
     someday
    0.06
     zosta
    0.06
     nghỉ
    0.06
     HttpNotFound
    0.06
    .CenterScreen
    0.06
    Act Density 0.370%

    No Known Activations