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

    Neuronpedia

    INDEX
    Explanations

    imperative verbs after "must"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     l
    1.23
    ご紹介
    1.21
    ous
    1.11
     n
    1.05
     k
    0.98
     to
    0.95
     q
    0.95
    ↵↵
    0.94
    ina
    0.94
    ymmetric
    0.93
    POSITIVE LOGITS
    다
    1.46
    te
    1.38
    ب
    1.36
    ا
    1.16
    و
    1.14
    ק
    1.14
    1
    1.13
    ta
    1.09
    ו
    1.09
    ري
    1.09
    Act Density 0.000%

    No Known Activations