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

    Neuronpedia

    INDEX
    Explanations

    examples and corrections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    리지
    -0.07
     неиз
    -0.07
     گردید
    -0.07
    Pieces
    -0.06
     збільш
    -0.06
    шими
    -0.06
     توضی
    -0.06
    耐
    -0.06
    -Cds
    -0.06
    claimed
    -0.06
    POSITIVE LOGITS
     cunt
    0.07
    .MON
    0.07
     ortalama
    0.06
     pilgr
    0.06
    .Alert
    0.06
    mail
    0.06
    PreparedStatement
    0.06
    kh
    0.06
    'http
    0.06
     Domain
    0.06
    Act Density 0.000%

    No Known Activations