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

    Neuronpedia

    INDEX
    Explanations

    code dependencies and tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ጥረ
    0.41
    樀
    0.41
    ٴ
    0.40
    頡
    0.39
    OGRAPHIC
    0.38
    ตรวจสอบ
    0.38
     मरीजों
    0.38
    考察
    0.38
    昶
    0.37
    数据库
    0.36
    POSITIVE LOGITS
    ayama
    0.41
    rbara
    0.40
    TRA
    0.37
    ారని
    0.36
    фф
    0.36
    ierra
    0.35
    сси
    0.35
    jších
    0.35
    ಂದ್ರ
    0.34
     тільки
    0.34
    Act Density 0.000%

    No Known Activations