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

    Neuronpedia

    INDEX
    Explanations

    Universal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🐿
    -0.08
    🍊
    -0.08
    _geometry
    -0.08
    啄
    -0.08
    ixo
    -0.07
    iltro
    -0.07
    .sensor
    -0.07
    .centerY
    -0.07
    Configurer
    -0.07
    刑事责任
    -0.07
    POSITIVE LOGITS
     العدو
    0.06
    :new
    0.06
    _constants
    0.06
     Unless
    0.06
    Ｐ
    0.06
     shopper
    0.06
    +]
    0.06
     murdered
    0.06
     implies
    0.06
    햊
    0.06
    Act Density 0.006%

    No Known Activations