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

    Neuronpedia

    INDEX
    Explanations

    Explanations and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Payment
    -0.06
     nasal
    -0.06
    .Localization
    -0.06
     tainted
    -0.06
     practice
    -0.06
     criticism
    -0.06
     Rupert
    -0.06
    Haunted
    -0.06
    بری
    -0.06
    ぅ
    -0.06
    POSITIVE LOGITS
    滿
    0.07
     مربوط
    0.07
    ='".$_
    0.06
     „
    0.06
     особенно
    0.06
     Kosovo
    0.06
    的大
    0.06
    ModelCreating
    0.06
     isSuccess
    0.06
     تف
    0.06
    Act Density 0.306%

    No Known Activations