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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .plus
    -0.07
     loser
    -0.07
     stroke
    -0.07
     Scheme
    -0.07
    ぇ
    -0.06
    ade
    -0.06
     Stroke
    -0.06
    avou
    -0.06
     procur
    -0.06
    _relu
    -0.06
    POSITIVE LOGITS
    (Of
    0.06
    cretion
    0.06
     обесп
    0.06
    ≡≡
    0.06
     із
    0.06
    按照
    0.06
    ────
    0.06
     отвеч
    0.06
     السكان
    0.06
    母
    0.06
    Act Density 0.048%

    No Known Activations