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

    Neuronpedia

    INDEX
    Explanations

    and / or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ients
    -0.13
    onas
    -0.12
     же
    -0.10
    phans
    -0.09
    пÑĢимеÑĢ
    -0.09
    اخر
    -0.09
    idon
    -0.08
    .DOM
    -0.08
    _HERSHEY
    -0.08
     and
    -0.08
    POSITIVE LOGITS
    /or
    0.83
    /OR
    0.44
     or
    0.38
    or
    0.38
    æĪĸèĢħ
    0.34
     ÛĮا
    0.31
     hoặc
    0.31
    æĪĸ
    0.31
     или
    0.29
     æĪĸ
    0.29
    Act Density 0.180%

    No Known Activations