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

    Neuronpedia

    INDEX
    Explanations

    balanced perspective and overview

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    h
    0.73
    os
    0.57
    as
    0.52
     will
    0.45
    ro
    0.44
    d
    0.43
    ILL
    0.43
    automatically
    0.43
    re
    0.43
    m
    0.42
    POSITIVE LOGITS
    ѧ
    0.51
    अप
    0.51
    Ყ
    0.50
     Batteries
    0.49
     errores
    0.47
     घरे
    0.47
     decorar
    0.47
     Tsh
    0.46
     oferty
    0.46
     décro
    0.45
    Act Density 0.007%

    No Known Activations