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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     為
    -0.07
    길
    -0.07
    ोर
    -0.06
    цвет
    -0.06
    تن
    -0.06
    ariance
    -0.06
    ELSE
    -0.06
     밀
    -0.06
     Ir
    -0.06
     توجه
    -0.06
    POSITIVE LOGITS
    vox
    0.07
    askan
    0.07
    Manual
    0.06
     cuckold
    0.06
    ToListAsync
    0.06
    ddit
    0.06
    -push
    0.06
    fastcall
    0.06
     polov
    0.06
     clase
    0.06
    Act Density 0.315%

    No Known Activations