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

    Neuronpedia

    INDEX
    Explanations

    checks, forecast,Nintendo, Bot, ChatGPT, time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     तब
    0.52
    á
    0.50
    uded
    0.46
     ይ
    0.46
     ป
    0.45
     podstaw
    0.45
    蒇
    0.45
    currentThread
    0.45
     ढ
    0.44
    reszt
    0.44
    POSITIVE LOGITS
     afforded
    0.50
     Elovl
    0.47
    得到了
    0.46
    لوب
    0.44
    ιάς
    0.44
    ডার
    0.43
     ubiquitin
    0.43
     gosto
    0.43
     vacuoles
    0.43
    োর্
    0.42
    Act Density 0.001%

    No Known Activations