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
     obdob
    -0.07
    ят
    -0.06
    FFE
    -0.06
    -util
    -0.06
    ียวก
    -0.06
     ADM
    -0.06
     thật
    -0.06
    PEC
    -0.06
    će
    -0.06
     Fiat
    -0.06
    POSITIVE LOGITS
    Of
    0.07
     OF
    0.07
     credits
    0.07
     To
    0.07
    .moves
    0.06
    Auf
    0.06
    numberOf
    0.06
     fools
    0.06
     NumberOf
    0.06
     hafta
    0.06
    Act Density 0.147%

    No Known Activations