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

    Neuronpedia

    INDEX
    Explanations

    orders, assembly, community, attacks, numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ieck
    0.53
     سلاټ
    0.51
    ̀i
    0.49
    and
    0.47
    ̣ng
    0.47
    ́p
    0.46
     riche
    0.46
     factorización
    0.45
    École
    0.45
     它
    0.43
    POSITIVE LOGITS
    ﯽ
    0.56
    இந்த
    0.55
    ﻪ
    0.54
    רא
    0.53
    товар
    0.52
    ي
    0.52
     sürec
    0.51
    ра
    0.51
    ra
    0.50
    дата
    0.49
    Act Density 0.080%

    No Known Activations