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

    Neuronpedia

    INDEX
    Explanations

    items in lists and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اهای
    0.32
     meist
    0.29
    کھوں
    0.28
     pertama
    0.28
    of
    0.27
     viu
    0.27
     svak
    0.27
     fleste
    0.27
     gehad
    0.27
    ならでは
    0.27
    POSITIVE LOGITS
     و
    0.29
     და
    0.29
    <0x0D>
    0.29
     등의
    0.29
     и
    0.28
     maritime
    0.28
    <unused2153>
    0.28
    ());
    0.27
     jeopardize
    0.26
     cowardly
    0.26
    Act Density 2.232%

    No Known Activations