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

    Neuronpedia

    INDEX
    Explanations

    sleepiness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ि
    1.09
    إ
    1.09
    ر
    1.04
    saraba
    0.98
    ام
    0.97
    ۰
    0.96
    🍖
    0.96
    に向けて
    0.95
    ?>"
    0.94
     de
    0.93
    POSITIVE LOGITS
    ية
    1.34
    ian
    1.07
     trebui
    1.05
    iego
    1.02
     başar
    1.00
     trastornos
    0.97
     ciertas
    0.91
     thức
    0.88
    breaking
    0.88
    kbar
    0.88
    Act Density 0.000%

    No Known Activations