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

    Neuronpedia

    INDEX
    Explanations

    PUT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    良
    -0.07
    奔
    -0.07
    ﯞ
    -0.06
    咳
    -0.06
     Gentle
    -0.06
    冠
    -0.06
    计
    -0.06
    お
    -0.06
    loon
    -0.06
     narratives
    -0.06
    POSITIVE LOGITS
    Boxes
    0.08
     שלי
    0.08
    _refer
    0.07
    ➡
    0.07
    WEEN
    0.07
    然后再
    0.07
    .DELETE
    0.07
     endangered
    0.07
    \"\
    0.07
    一直都是
    0.07
    Act Density 0.003%

    No Known Activations