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

    Neuronpedia

    INDEX
    Explanations

    past-tense verbs and specific formatted terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    1.08
    ofd
    0.96
     électrique
    0.96
    ଆ
    0.96
     î
    0.93
    お
    0.91
     și
    0.89
    昰
    0.89
     Și
    0.87
    おしゃれ
    0.86
    POSITIVE LOGITS
    ت
    2.09
    س
    1.63
    с
    1.55
    т
    1.40
    ed
    1.32
    et
    1.32
    त
    1.27
    و
    1.27
    تهم
    1.23
    i
    1.23
    Act Density 1.329%

    No Known Activations