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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .isConnected
    -0.07
    лось
    -0.07
    нике
    -0.07
     Rox
    -0.06
    ayi
    -0.06
    _PATTERN
    -0.06
     Snyder
    -0.06
    序
    -0.06
    něn
    -0.06
    Bomb
    -0.06
    POSITIVE LOGITS
    条件
    0.07
     whipping
    0.07
    aliases
    0.06
     instant
    0.06
    简
    0.06
     zda
    0.06
     تجاری
    0.06
    хови
    0.06
     Meat
    0.06
    culus
    0.06
    Act Density 0.002%

    No Known Activations