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

    Neuronpedia

    INDEX
    Explanations

    likelihood

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ницы
    -0.08
    ांस
    -0.08
    ुओं
    -0.07
     управления
    -0.07
    ുകള
    -0.07
    eback
    -0.07
    pi
    -0.07
    اقة
    -0.07
     mij
    -0.07
    /import
    -0.07
    POSITIVE LOGITS
     occurrence
    0.11
     probability
    0.11
    Probability
    0.10
    _probability
    0.10
     probabilities
    0.10
    دوث
    0.10
     Probability
    0.10
     وقوع
    0.10
    성이
    0.10
     вероятность
    0.09
    Act Density 0.002%

    No Known Activations