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

    Neuronpedia

    INDEX
    Explanations

    Code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     решения
    -0.07
    (parser
    -0.07
     прит
    -0.07
     kt
    -0.06
    /wait
    -0.06
     ناب
    -0.06
    -0.06
    .Contract
    -0.06
    _confirmation
    -0.06
     ศร
    -0.06
    POSITIVE LOGITS
     hates
    0.06
     Parti
    0.06
    omain
    0.06
    Meta
    0.06
    ulously
    0.06
     lar
    0.06
    сии
    0.06
    رفت
    0.06
     Powered
    0.06
     TJ
    0.06
    Act Density 0.019%

    No Known Activations