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

    Neuronpedia

    INDEX
    Explanations

    ratings or levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RDONLY
    -0.07
     váž
    -0.07
    ='<?
    -0.07
     hakkında
    -0.07
     centers
    -0.07
     vedení
    -0.06
     tarih
    -0.06
     ⇒
    -0.06
     tanggal
    -0.06
     wollte
    -0.06
    POSITIVE LOGITS
    lal
    0.06
    oso
    0.06
    омен
    0.06
    _SL
    0.06
     Wen
    0.06
    登录
    0.06
    osed
    0.06
    اظ
    0.06
    Quote
    0.06
     final
    0.05
    Act Density 0.032%

    No Known Activations