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

    Neuronpedia

    INDEX
    Explanations

    platform APIs and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    0.73
    of
    0.73
    g
    0.73
    at
    0.72
    c
    0.72
    be
    0.66
    t
    0.66
    ge
    0.65
    l
    0.65
    ล
    0.64
    POSITIVE LOGITS
     plataforma
    1.19
     plataformas
    1.19
     piattaforma
    1.16
     platform
    1.07
     Platform
    1.05
     plateforme
    1.04
    '
    1.02
     플랫폼
    0.96
     Plattform
    0.95
     dirigentes
    0.94
    Act Density 0.034%

    No Known Activations