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

    Neuronpedia

    INDEX
    Explanations

    approximate computing and refinement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    خدم
    0.50
    عب
    0.49
    data
    0.48
    Cap
    0.48
    ु
    0.48
    s
    0.48
    the
    0.47
    ﺑ
    0.46
    ू
    0.46
    رفع
    0.45
    POSITIVE LOGITS
     rmse
    0.52
    byter
    0.48
     הפר
    0.48
     elke
    0.48
     nieuw
    0.47
     rjf
    0.46
     r
    0.46
     응
    0.45
     asympt
    0.45
    と同様
    0.45
    Act Density 0.000%

    No Known Activations