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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ختم
    -0.09
    nande
    -0.09
     Yam
    -0.08
    ouv
    -0.08
    arning
    -0.08
    iete
    -0.08
    eking
    -0.08
     lute
    -0.07
     grape
    -0.07
    .infinity
    -0.07
    POSITIVE LOGITS
    累计
    0.11
     μει
    0.09
     cumulative
    0.09
     congest
    0.08
     accrued
    0.08
     comprim
    0.08
     augmenter
    0.08
     incorporates
    0.08
     compensated
    0.08
    скаж
    0.08
    Act Density 0.010%

    No Known Activations