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

    Neuronpedia

    INDEX
    Explanations

    processing numbers and generating results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     את
    0.58
     चाहे
    0.48
     सम
    0.47
     ollut
    0.46
     the
    0.45
     (
    0.45
     ప్రస్తుతం
    0.44
     tegen
    0.43
     থাকতেন
    0.43
     اﻻ
    0.42
    POSITIVE LOGITS
    ی
    0.57
    it
    0.52
    ه
    0.52
    רו
    0.50
    س
    0.48
    ৫
    0.47
    IX
    0.47
    سی
    0.46
    INI
    0.46
    پ
    0.45
    Act Density 0.019%

    No Known Activations