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

    Neuronpedia

    INDEX
    Explanations

    stats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     :＼
    -0.07
     наличи
    -0.06
     ať
    -0.06
     çab
    -0.06
     المللی
    -0.06
     çevres
    -0.06
     misguided
    -0.06
    _hour
    -0.06
     лишь
    -0.06
     ｜
    -0.06
    POSITIVE LOGITS
    Slim
    0.07
     Stats
    0.07
    Stats
    0.06
     GM
    0.06
    stats
    0.06
    Forum
    0.06
     Tex
    0.06
     dorm
    0.06
     ممن
    0.06
     Flexible
    0.06
    Act Density 0.011%

    No Known Activations