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

    Neuronpedia

    INDEX
    Explanations

    excessive graphic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nonzero
    0.47
    훨
    0.43
    Rez
    0.42
    sne
    0.42
    ActivityCompat
    0.42
    yaratan
    0.39
    sneak
    0.39
    ériences
    0.38
    FAQs
    0.38
    ⠀
    0.38
    POSITIVE LOGITS
     excessive
    1.41
    Excess
    1.35
     Excessive
    1.34
    excess
    1.31
     eccess
    1.29
     excess
    1.23
     Excess
    1.21
     exces
    1.20
     excessively
    1.15
     excesses
    1.10
    Act Density 0.734%

    No Known Activations