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

    Neuronpedia

    INDEX
    Explanations

    _SYS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     멀
    -0.07
     escaping
    -0.07
     confession
    -0.06
    Cog
    -0.06
     glamour
    -0.06
     Wolves
    -0.06
     exh
    -0.06
     بشر
    -0.06
     disposed
    -0.06
     fileId
    -0.06
    POSITIVE LOGITS
    .recv
    0.07
    abilecek
    0.06
    。。
    0.06
    rome
    0.06
     Registr
    0.06
    DK
    0.06
    orderby
    0.06
     розп
    0.06
    struk
    0.06
    ］
    0.06
    Act Density 0.002%

    No Known Activations