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

    Neuronpedia

    INDEX
    Explanations

    calories and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اک
    0.29
    ጐ
    0.29
    ല്ലാതെ
    0.27
    ʝ
    0.27
    Ids
    0.27
    觎
    0.26
    境界層
    0.26
     વસ્તુ
    0.25
    မြို့
    0.25
    स्तेमाल
    0.25
    POSITIVE LOGITS
    6
    0.70
    5
    0.69
    8
    0.68
    7
    0.65
    0.61
    9
    0.59
    4
    0.57
    1
    0.55
     ۱۵
    0.54
     ۵
    0.53
    Act Density 0.403%

    No Known Activations