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

    Neuronpedia

    INDEX
    Explanations

    coefficient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ер
    0.43
    ínguez
    0.42
     داله
    0.42
    кура
    0.41
     erupt
    0.41
    dol
    0.40
    دول
    0.39
     Polska
    0.39
     Erg
    0.39
     expt
    0.38
    POSITIVE LOGITS
     coefficients
    0.66
     coefficient
    0.63
    coefficients
    0.63
    coefficient
    0.61
     coeficiente
    0.52
    Coefficient
    0.51
     коэффици
    0.51
     coef
    0.50
    系数
    0.50
     coeff
    0.49
    Act Density 0.001%

    No Known Activations