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

    Neuronpedia

    INDEX
    Explanations

    burden

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    azor
    -0.07
     winner
    -0.06
    /db
    -0.06
     чтобы
    -0.06
    /change
    -0.06
    _od
    -0.06
    >:</
    -0.06
    aving
    -0.06
    .cr
    -0.06
     ary
    -0.06
    POSITIVE LOGITS
    очные
    0.07
    错
    0.07
    (INT
    0.07
     sci
    0.06
    ματα
    0.06
     electronic
    0.06
    ونية
    0.06
     Reaction
    0.06
    -class
    0.06
     Fresh
    0.06
    Act Density 0.023%

    No Known Activations