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

    Neuronpedia

    INDEX
    Explanations

    Code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sistema
    -0.07
     dipped
    -0.07
    .he
    -0.06
     tạm
    -0.06
    Ka
    -0.06
    مانی
    -0.06
    шибка
    -0.06
     simplified
    -0.06
     AREA
    -0.06
    .Code
    -0.06
    POSITIVE LOGITS
    taboola
    0.06
     pornofil
    0.06
    :ss
    0.06
    ení
    0.06
     tỏ
    0.06
    통령
    0.06
    負
    0.06
    _cache
    0.05
     cpp
    0.05
    641
    0.05
    Act Density 0.020%

    No Known Activations