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

    Neuronpedia

    INDEX
    Explanations

    parentheses or code notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fah
    0.46
     oh
    0.45
    라고
    0.44
    ൻ
    0.44
     put
    0.43
    re
    0.42
    0.41
     perkembangan
    0.41
     icing
    0.40
    볼
    0.40
    POSITIVE LOGITS
     अन्यथा
    0.45
     एनिमल
    0.44
     (-\
    0.44
     unfounded
    0.44
     trasm
    0.43
    তাসীন
    0.41
     practised
    0.41
    ^{-}
    0.40
     الواي
    0.40
     матри
    0.40
    Act Density 0.000%

    No Known Activations