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

    Neuronpedia

    INDEX
    Explanations

    analysis and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۔
    0.34
     P
    0.34
     എന്നീ
    0.33
    P
    0.31
     Makefile
    0.31
     дальнейшем
    0.30
     һәм
    0.30
     ۽
    0.30
     Amerikaanse
    0.29
    พ์
    0.28
    POSITIVE LOGITS
    sächlich
    0.48
    heureusement
    0.48
    istically
    0.47
     ensues
    0.47
     abound
    0.46
     varies
    0.46
     occurs
    0.46
     ranges
    0.44
     galore
    0.42
    lessly
    0.42
    Act Density 0.044%

    No Known Activations