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

    Neuronpedia

    INDEX
    Explanations

    population density

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    upertino
    -0.07
     stringWith
    -0.07
     Sơn
    -0.06
    âk
    -0.06
    _ENC
    -0.06
     abych
    -0.06
     yaptır
    -0.06
    nect
    -0.06
     CONVERT
    -0.06
    َأ
    -0.06
    POSITIVE LOGITS
    ──
    0.08
     experimented
    0.06
     الأمريكي
    0.06
    positive
    0.06
     LOL
    0.06
     verbally
    0.06
    に出
    0.06
     prakt
    0.06
    /><
    0.06
    分类
    0.06
    Act Density 0.003%

    No Known Activations