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

    Neuronpedia

    INDEX
    Explanations

    Code related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lex
    -0.08
     spotify
    -0.07
    -bar
    -0.07
    🥚
    -0.07
     Id
    -0.07
    .GraphicsUnit
    -0.07
     OWN
    -0.06
    .baseUrl
    -0.06
    葭
    -0.06
    六十
    -0.06
    POSITIVE LOGITS
    _Generic
    0.08
    &nbsp
    0.07
    תן
    0.07
    !important
    0.07
    发明
    0.07
    _masks
    0.07
     setzen
    0.07
    lei
    0.07
    פתיחת
    0.07
    科技
    0.07
    Act Density 0.012%

    No Known Activations