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

    Neuronpedia

    INDEX
    Explanations

    conjug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    샌
    -0.08
    נא
    -0.07
    �
    -0.07
    湛
    -0.07
    camera
    -0.07
    _bias
    -0.06
    尊严
    -0.06
    ikes
    -0.06
    Sand
    -0.06
     bloom
    -0.06
    POSITIVE LOGITS
    arefa
    0.08
    URAL
    0.07
    玤
    0.07
    <QString
    0.07
    \common
    0.07
    eam
    0.06
    等方式
    0.06
    ugu
    0.06
    蓖
    0.06
    ları
    0.06
    Act Density 0.003%

    No Known Activations