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

    Neuronpedia

    INDEX
    Explanations

    excitement, funk, countable value creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NRA
    0.46
    f
    0.44
    in
    0.43
     BRO
    0.43
    rl
    0.42
     SPL
    0.42
     PPC
    0.41
    rs
    0.41
    time
    0.40
    izin
    0.40
    POSITIVE LOGITS
    ൂ
    0.54
     ଏ
    0.47
    ચા
    0.45
    戽
    0.44
     десять
    0.43
    ERE
    0.43
     ۽
    0.42
    呵呵
    0.41
     алуу
    0.41
    ቱን
    0.41
    Act Density 0.002%

    No Known Activations