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

    Neuronpedia

    INDEX
    Explanations

    for loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    য়ান
    0.69
    ا
    0.63
    bts
    0.63
    هام
    0.62
    iczny
    0.61
     sikap
    0.61
    mselves
    0.61
    Исто
    0.60
     sebenarnya
    0.60
    ių
    0.59
    POSITIVE LOGITS
     मिळते
    0.76
    ≤
    0.73
    해서
    0.70
     facile
    0.70
     parthenogenetic
    0.69
    υ
    0.68
    ≠
    0.68
     isinstance
    0.68
     υπάρχει
    0.67
    Makefile
    0.66
    Act Density 0.000%

    No Known Activations