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

    Neuronpedia

    INDEX
    Explanations

    affirmations and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Bounds
    -0.07
    秀
    -0.07
    THR
    -0.07
    dates
    -0.07
    [],↵
    -0.06
     ks
    -0.06
    (br
    -0.06
    Restricted
    -0.06
    irable
    -0.06
    ン
    -0.06
    POSITIVE LOGITS
     AUX
    0.07
    .getChild
    0.06
     віз
    0.06
     ов
    0.06
    .componentInstance
    0.06
     IMAGE
    0.06
     localObject
    0.06
    되는
    0.06
     TensorFlow
    0.06
     breakfast
    0.06
    Act Density 0.174%

    No Known Activations