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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     posicion
    -0.07
     Mo
    -0.07
    quee
    -0.06
     jim
    -0.06
    air
    -0.06
    (setting
    -0.06
    Six
    -0.06
    Strip
    -0.06
    _closure
    -0.06
     시험
    -0.06
    POSITIVE LOGITS
     диаг
    0.08
     вироб
    0.07
    訳
    0.07
    _help
    0.07
     titleLabel
    0.07
     sparking
    0.07
    dorf
    0.06
    <K
    0.06
    เพลง
    0.06
     kcal
    0.06
    Act Density 0.109%

    No Known Activations