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

    Neuronpedia

    INDEX
    Explanations

    code and system metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ్రు
    0.61
     debo
    0.59
    躯
    0.57
    bib
    0.57
     weep
    0.56
    uiscono
    0.55
     subsec
    0.55
    ङ
    0.54
     मल
    0.54
    онер
    0.54
    POSITIVE LOGITS
     установ
    0.73
    قوم
    0.71
    навли
    0.70
    转换
    0.66
    টুকু
    0.65
     прове
    0.64
     서
    0.64
     promove
    0.63
    瀚
    0.63
     Из
    0.63
    Act Density 0.066%

    No Known Activations