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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cake
    -0.07
    signal
    -0.06
     Sick
    -0.06
    疗
    -0.06
    silver
    -0.06
     sociales
    -0.06
    Ir
    -0.06
     ngắn
    -0.06
     SHORT
    -0.06
     Ames
    -0.06
    POSITIVE LOGITS
     Mary
    0.07
     tous
    0.07
    missible
    0.07
     하나
    0.07
    .ListView
    0.07
    ダ
    0.06
    lename
    0.06
     Grund
    0.06
    _diff
    0.06
     vais
    0.06
    Act Density 0.024%

    No Known Activations