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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EXAMPLE
    -0.07
    ﾗ
    -0.07
     ire
    -0.07
    汉语
    -0.07
    ippo
    -0.06
     cœur
    -0.06
    之後
    -0.06
    _mu
    -0.06
    _PLUGIN
    -0.06
     Таким
    -0.06
    POSITIVE LOGITS
    ervatives
    0.07
     Stores
    0.07
     pent
    0.07
    ("!
    0.07
     Borders
    0.07
    冥
    0.07
    빡
    0.07
    到位
    0.07
     flow
    0.07
    促成
    0.06
    Act Density 0.000%

    No Known Activations