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

    Neuronpedia

    INDEX
    Explanations

    describes phenomena occurring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.52
    🅘
    0.48
    <0x9C>
    0.48
    м
    0.45
     μέσω
    0.45
    cdZ
    0.44
    via
    0.43
    此
    0.43
    Sebelum
    0.42
    i
    0.42
    POSITIVE LOGITS
     upright
    0.47
     rightfully
    0.45
     agh
    0.45
     incompar
    0.45
     comparatively
    0.43
     enthr
    0.42
     repar
    0.41
     öğrend
    0.41
     justifica
    0.41
     habitual
    0.41
    Act Density 0.001%

    No Known Activations