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

    Neuronpedia

    INDEX
    Explanations

    avoiding skinny, not perfectly, industrial applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flywheel
    0.41
     incubating
    0.39
    iflower
    0.38
    ambah
    0.37
    endi
    0.37
    ophosphate
    0.36
     incubation
    0.36
     snippet
    0.35
    estock
    0.35
     mosaic
    0.35
    POSITIVE LOGITS
     vezes
    0.46
     हद
    0.46
     veces
    0.46
    them
    0.44
     fish
    0.43
     bitches
    0.41
     times
    0.40
     volte
    0.40
     them
    0.39
    这一切
    0.39
    Act Density 0.000%

    No Known Activations