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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cond
    -0.07
    sin
    -0.07
    _ment
    -0.06
    increment
    -0.06
    StateException
    -0.06
     guidelines
    -0.06
    Pay
    -0.06
    .preferences
    -0.06
    Regressor
    -0.06
     inflated
    -0.06
    POSITIVE LOGITS
     محمود
    0.07
    _WAKE
    0.07
     قادر
    0.07
     Доб
    0.07
    ्वच
    0.07
     teardown
    0.07
     หาก
    0.06
    -establish
    0.06
     olmadı
    0.06
     Çocuk
    0.06
    Act Density 0.038%

    No Known Activations