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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    0.86
     unsurpassed
    0.67
     unable
    0.65
     underestimate
    0.64
     unwavering
    0.64
     unrival
    0.64
     газ
    0.63
    ية
    0.63
    ة
    0.62
     impede
    0.61
    POSITIVE LOGITS
    t
    1.12
    おります
    0.97
    x
    0.88
    ри
    0.81
    но
    0.78
    на
    0.73
    ни
    0.73
    el
    0.72
    xn
    0.71
    ног
    0.70
    Act Density 0.173%

    No Known Activations