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

    Neuronpedia

    INDEX
    Explanations

    term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     αποκ
    -0.09
     Sequential
    -0.08
     Jour
    -0.08
     تقوم
    -0.08
     έναν
    -0.08
    ایک
    -0.08
    ယူ
    -0.07
     πραγματοποι
    -0.07
     verdict
    -0.07
     Respect
    -0.07
    POSITIVE LOGITS
     coeff
    0.09
     quadratic
    0.09
    .--
    0.08
     symmetrical
    0.08
     kosong
    0.08
     coefficient
    0.08
     coefficients
    0.08
     coef
    0.08
    coeff
    0.08
    Coefficient
    0.08
    Act Density 0.014%

    No Known Activations