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

    Neuronpedia

    INDEX
    Explanations

    mathematical/code notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     магни
    0.34
    ◞
    0.28
     aportar
    0.28
    бавить
    0.28
     加
    0.26
     全
    0.26
     contentService
    0.26
    морфи
    0.25
    eteers
    0.25
    照明
    0.25
    POSITIVE LOGITS
     પ્રકાર
    0.34
    jangan
    0.29
     frequência
    0.28
     longtime
    0.28
    જન
    0.28
     kan
    0.27
     جبکہ
    0.27
    一周
    0.27
     বিশেষভাবে
    0.27
    ясь
    0.27
    Act Density 0.004%

    No Known Activations