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

    Neuronpedia

    INDEX
    Explanations

    /**

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     because
    -0.07
    &e
    -0.07
    %C
    -0.07
     ensemble
    -0.07
     highlighted
    -0.07
    完
    -0.06
    ANS
    -0.06
    事业单位
    -0.06
     StatusCode
    -0.06
     candidate
    -0.06
    POSITIVE LOGITS
    一手
    0.07
     RR
    0.07
    caught
    0.07
    Sources
    0.07
     dragged
    0.07
    _SA
    0.07
    ráf
    0.06
    (urls
    0.06
    discord
    0.06
     coached
    0.06
    Act Density 0.011%

    No Known Activations