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

    Neuronpedia

    INDEX
    Explanations

    Code/Logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Malays
    -0.07
     Bau
    -0.07
    醒
    -0.07
    Inicio
    -0.06
    _positive
    -0.06
    stakes
    -0.06
     soutě
    -0.06
     فريق
    -0.06
    kaz
    -0.06
    718
    -0.06
    POSITIVE LOGITS
     donna
    0.07
    ORMAL
    0.06
     fuck
    0.06
     عالی
    0.06
     parce
    0.06
     Hotel
    0.06
    :g
    0.06
     chiropr
    0.06
     quan
    0.06
     характ
    0.06
    Act Density 0.000%

    No Known Activations