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

    Neuronpedia

    INDEX
    Explanations

    band

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ￠
    -0.08
     Ive
    -0.07
    .assertIs
    -0.07
    _INTER
    -0.07
     verw
    -0.07
     imaginary
    -0.07
    posé
    -0.06
     남
    -0.06
    brakk
    -0.06
    新时代
    -0.06
    POSITIVE LOGITS
    avigation
    0.08
    셜
    0.07
    _Height
    0.07
     bü
    0.07
    Hora
    0.07
    tabla
    0.07
    ę
    0.07
    בח
    0.07
    ного
    0.07
    Separator
    0.06
    Act Density 0.003%

    No Known Activations