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

    Neuronpedia

    INDEX
    Explanations

    pronouns and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     እየሱስ
    0.50
     सम्बन्ध
    0.49
     রচন
    0.49
     Sine
    0.48
    GEBURTS
    0.47
     ಸಂಸ್ಥ
    0.46
    垭
    0.46
     চাষ
    0.46
     پیغم
    0.46
    Paw
    0.46
    POSITIVE LOGITS
    s
    0.64
     or
    0.59
     is
    0.52
     in
    0.52
     (
    0.48
    (
    0.48
     and
    0.48
    n
    0.45
    h
    0.45
     one
    0.45
    Act Density 0.002%

    No Known Activations