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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adget
    -0.08
    asjon
    -0.07
    axies
    -0.07
     nicotine
    -0.07
     Nz
    -0.07
    ترو
    -0.07
    opoly
    -0.07
    Ник
    -0.07
    เ
    -0.06
     institution
    -0.06
    POSITIVE LOGITS
    評
    0.07
    呇
    0.07
    氢
    0.07
     estamos
    0.07
    :value
    0.07
    mil
    0.07
    ocado
    0.06
    .lex
    0.06
    Vtbl
    0.06
    חת
    0.06
    Act Density 0.058%

    No Known Activations