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

    Neuronpedia

    INDEX
    Explanations

    comparison tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     topi
    0.44
     других
    0.41
     inne
    0.41
    |
    0.41
     δύ
    0.40
     mle
    0.40
     inde
    0.40
     сле
    0.39
     інших
    0.39
     Bi
    0.39
    POSITIVE LOGITS
    ydia
    0.42
    ನಾಟಕ
    0.40
     xbox
    0.40
    ParseException
    0.40
    StubCompat
    0.39
    hander
    0.39
     Spielen
    0.39
     assures
    0.38
    ikopter
    0.38
    gaming
    0.38
    Act Density 0.005%

    No Known Activations