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

    Neuronpedia

    INDEX
    Explanations

    included notes explanations options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    หรือ
    0.38
     অথবা
    0.38
     અથવા
    0.37
     किंवा
    0.36
     अथवा
    0.36
    あるいは
    0.36
     veya
    0.33
     hoặc
    0.33
    ภาค
    0.33
     unfolds
    0.33
    POSITIVE LOGITS
    et
    0.39
     only
    0.38
     tried
    0.38
    pt
    0.36
     very
    0.36
    ys
    0.35
    na
    0.35
    きましたが
    0.35
    了一种
    0.35
    しましたが
    0.35
    Act Density 0.160%

    No Known Activations