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

    Neuronpedia

    INDEX
    Explanations

    char pointer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oczywiście
    0.41
    اگر
    0.40
     aquel
    0.38
    う
    0.38
    άν
    0.37
     ذوالفقار
    0.37
    สำหรับ
    0.37
     Ansari
    0.37
    步行
    0.37
    ception
    0.36
    POSITIVE LOGITS
     वीडियो
    0.46
     भाषा
    0.42
    鈳
    0.41
     نوا
    0.41
    ﻛ
    0.41
    वेयर
    0.40
     అన్ని
    0.40
     வெப்ப
    0.40
     गर्मी
    0.40
     វា
    0.40
    Act Density 0.002%

    No Known Activations