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

    Neuronpedia

    INDEX
    Explanations

    valid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kuru
    -0.06
    Lost
    -0.06
     Frankie
    -0.06
     repetitive
    -0.06
    <input
    -0.06
     reach
    -0.06
    اقة
    -0.06
     bekommen
    -0.06
     beautifully
    -0.06
    .fre
    -0.06
    POSITIVE LOGITS
    .toJSONString
    0.07
    ulaire
    0.07
    ‡
    0.07
    XY
    0.07
    _DEF
    0.07
    Tipo
    0.06
     квад
    0.06
    -marker
    0.06
    VIC
    0.06
    _MAGIC
    0.06
    Act Density 0.012%

    No Known Activations