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

    Neuronpedia

    INDEX
    Explanations

    non-english or definitions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anum
    -0.08
     bepaalde
    -0.08
    Adr
    -0.08
     ciertas
    -0.08
     certain
    -0.08
     és
    -0.08
     Certain
    -0.08
     wea
    -0.08
     certaines
    -0.07
     habido
    -0.07
    POSITIVE LOGITS
    ’den
    0.09
     詳
    0.08
    _safe
    0.07
    trusted
    0.07
    :list
    0.07
     trusted
    0.07
    0.07
    ീസ
    0.07
     summar
    0.07
     detailed
    0.07
    Act Density 0.004%
    No Known Activations