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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ctp
    -0.07
     Goblin
    -0.07
     روم
    -0.06
    dyby
    -0.06
     pushing
    -0.06
     Hand
    -0.06
    clf
    -0.06
    ANTA
    -0.06
     gode
    -0.06
    Fraction
    -0.06
    POSITIVE LOGITS
    "),"
    0.08
    (),"
    0.07
     \"%
    0.06
     luc
    0.06
     tấm
    0.06
    装
    0.06
     alas
    0.06
    .dirname
    0.06
     extremes
    0.06
     золот
    0.06
    Act Density 0.052%

    No Known Activations