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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ाऊ
    -0.06
     VII
    -0.06
     jestli
    -0.06
    Dr
    -0.06
    عاد
    -0.06
     answered
    -0.06
    .Str
    -0.06
     rejected
    -0.06
    显示
    -0.06
     neuken
    -0.06
    POSITIVE LOGITS
    ﺮ
    0.07
     hexadecimal
    0.06
     proprio
    0.06
    řich
    0.06
    -mobile
    0.06
    (chain
    0.06
     shorter
    0.06
     cadena
    0.06
     assortment
    0.06
    arga
    0.06
    Act Density 0.012%

    No Known Activations