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

    Neuronpedia

    INDEX
    Explanations

    acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    އ
    0.60
    د
    0.55
    સ
    0.54
    дку
    0.53
    šanu
    0.52
    ষধ
    0.52
    Во
    0.51
    ግዳ
    0.49
    Не
    0.49
    বৃদ্ধি
    0.49
    POSITIVE LOGITS
    '
    0.91
    e
    0.67
    p
    0.66
    er
    0.63
     was
    0.63
     are
    0.61
    ing
    0.59
    en
    0.58
    ed
    0.57
    et
    0.55
    Act Density 0.421%

    No Known Activations