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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的回答
    -0.07
     yaz
    -0.07
    進入
    -0.07
     duration
    -0.07
    coords
    -0.07
    摹
    -0.06
    RectTransform
    -0.06
    通常是
    -0.06
     Burb
    -0.06
     REUTERS
    -0.06
    POSITIVE LOGITS
     Venez
    0.08
    ----------
↵
    0.07
    .Serializable
    0.07
    (sf
    0.07
    //----------------
    0.07
    さんが
    0.07
     ситу
    0.07
    פש
    0.07
    picable
    0.07
    EndInit
    0.06
    Act Density 0.001%

    No Known Activations