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

    Neuronpedia

    INDEX
    Explanations

    or alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /licenses
    -0.10
    OrNull
    -0.09
    kest
    -0.09
    serter
    -0.08
    âh
    -0.08
    styleType
    -0.08
    '&&
    -0.08
    ì£
    -0.08
    /Dk
    -0.08
    759
    -0.08
    POSITIVE LOGITS
     or
    0.44
    æĪĸ
    0.32
     или
    0.28
     hoặc
    0.25
     ÛĮا
    0.25
    หร
    0.24
     veya
    0.22
     atau
    0.22
     oder
    0.21
    ê±°ëĤĺ
    0.21
    Act Density 0.405%

    No Known Activations