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

    Neuronpedia

    INDEX
    Explanations

    у

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Silver
    -0.07
    .codes
    -0.07
     highway
    -0.07
     Snyder
    -0.06
    $max
    -0.06
     Rodr
    -0.06
     Glam
    -0.06
    Precision
    -0.06
    Silver
    -0.06
     Bol
    -0.06
    POSITIVE LOGITS
    ディース
    0.08
     kendisi
    0.07
    ンク
    0.06
    реп
    0.06
    ідом
    0.06
    berapa
    0.06
    при
    0.06
    fills
    0.06
    وص
    0.06
    圖
    0.06
    Act Density 0.004%

    No Known Activations