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

    Neuronpedia

    INDEX
    Explanations

    following specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NaHCO
    0.83
     prostatitis
    0.78
    ICPSR
    0.78
    olaire
    0.78
     uranyl
    0.74
    aminophen
    0.74
    anamh
    0.73
     proteinuria
    0.72
    ImageFilter
    0.72
    acuda
    0.72
    POSITIVE LOGITS
    នូវ
    0.61
     તેના
    0.57
     ফ
    0.57
     ફ
    0.55
     those
    0.53
     هایی
    0.52
     втором
    0.51
     دیے
    0.51
     ۴
    0.50
     அதே
    0.50
    Act Density 0.152%

    No Known Activations