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

    Neuronpedia

    INDEX
    Explanations

    lig, cit, bud, val, prom, assis, writ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \)
    0.54
    ногда
    0.48
    ﻴ
    0.47
     ribbed
    0.46
     pelo
    0.46
    वायरस
    0.44
    ...\...\
    0.44
    젹
    0.44
    ётся
    0.44
    \
    0.44
    POSITIVE LOGITS
    as
    0.63
    at
    0.61
    et
    0.61
    c
    0.59
    u
    0.59
    r
    0.57
    w
    0.52
    n
    0.50
    ar
    0.50
    am
    0.50
    Act Density 0.063%

    No Known Activations