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

    Neuronpedia

    INDEX
    Explanations

    ctype

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aul
    -0.08
     =============================================================================↵
    -0.06
     Bols
    -0.06
    _SD
    -0.06
     така
    -0.06
     realised
    -0.06
    IPv
    -0.06
    ому
    -0.06
    writers
    -0.06
     ironic
    -0.06
    POSITIVE LOGITS
     sınav
    0.07
    @example
    0.07
     بررسی
    0.07
    ienda
    0.07
    (Token
    0.06
    unt
    0.06
    tero
    0.06
     Xã
    0.06
     Vote
    0.06
     双线
    0.06
    Act Density 0.001%

    No Known Activations