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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uyến
    -0.07
    Ci
    -0.07
     gazet
    -0.07
    انیا
    -0.07
     Rt
    -0.06
     другим
    -0.06
    ［
    -0.06
     disap
    -0.06
     شم
    -0.06
    лася
    -0.06
    POSITIVE LOGITS
     |_|
    0.07
     dataframe
    0.06
    geom
    0.06
     fetisch
    0.06
     erotique
    0.06
     snake
    0.06
    281
    0.06
     Douglas
    0.06
    (news
    0.06
    _mono
    0.06
    Act Density 0.008%

    No Known Activations