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

    Neuronpedia

    INDEX
    Explanations

    6

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ỏ
    -0.07
    支付
    -0.07
    UTH
    -0.07
    แสดง
    -0.07
    再
    -0.07
    作为一名
    -0.07
    Serialization
    -0.06
    лат
    -0.06
    restaurant
    -0.06
     already
    -0.06
    POSITIVE LOGITS
    _hr
    0.07
     freezing
    0.07
    立场
    0.07
    ✙
    0.07
     Pré
    0.07
     międzynar
    0.07
     helf
    0.07
     mould
    0.07
     shaping
    0.07
    POINT
    0.07
    Act Density 0.003%

    No Known Activations