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

    Neuronpedia

    INDEX
    Explanations

    or or separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    atthakath
    0.21
    ഹ്ലാദ
    0.21
     BLUENRG
    0.21
    getFull
    0.21
     immédi
    0.21
     গবে
    0.20
     uncorrelated
    0.20
    Issledovatel
    0.20
    𒈬
    0.20
    <unused682>
    0.20
    POSITIVE LOGITS
     veya
    0.36
    ’
    0.34
    或其他
    0.34
     or
    0.33
    /
    0.31
     أو
    0.29
     или
    0.29
     atau
    0.28
     ataupun
    0.28
     alebo
    0.27
    Act Density 3.385%

    No Known Activations