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

    Neuronpedia

    INDEX
    Explanations

    average

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sarc
    -0.08
     Mobile
    -0.07
    日
    -0.07
    unted
    -0.06
    aras
    -0.06
    ‌د
    -0.06
     cityName
    -0.06
    ocab
    -0.06
    ัด
    -0.06
     kuru
    -0.06
    POSITIVE LOGITS
     nuôi
    0.07
    ([[
    0.06
    356
    0.06
    abr
    0.06
     milf
    0.06
     Missile
    0.06
    둥
    0.06
    Dod
    0.06
    asser
    0.06
     ارسال
    0.06
    Act Density 0.018%

    No Known Activations