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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tickets
    -0.06
     nước
    -0.06
     okam
    -0.06
    тер
    -0.06
    rowned
    -0.06
    !<
    -0.06
    층
    -0.06
     �
    -0.05
    بات
    -0.05
     sıras
    -0.05
    POSITIVE LOGITS
     Breaking
    0.07
     sess
    0.07
     farmer
    0.07
     Gross
    0.07
     Phrase
    0.07
     resizeMode
    0.06
    ouston
    0.06
    .urlopen
    0.06
     gint
    0.06
    _Selection
    0.06
    Act Density 0.021%

    No Known Activations