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
    _diff
    -0.07
     fuss
    -0.07
     flips
    -0.07
    ач
    -0.07
    懈
    -0.07
    hz
    -0.07
    娃
    -0.06
    传球
    -0.06
     sóc
    -0.06
     ang
    -0.06
    POSITIVE LOGITS
    .thumbnail
    0.09
    domain
    0.08
     swallowed
    0.08
    全域
    0.08
    &oacute
    0.07
     joyful
    0.07
    🚼
    0.07
    .memory
    0.07
    .document
    0.07
    �
    0.07
    Act Density 0.003%

    No Known Activations