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

    Neuronpedia

    INDEX
    Explanations

    being judged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eyel
    0.48
     바로
    0.42
     दृश्य
    0.39
     dipl
    0.38
     गड़ब
    0.38
     иллю
    0.37
     våra
    0.37
     fault
    0.37
    kách
    0.37
    âche
    0.36
    POSITIVE LOGITS
     bzw
    0.49
     estudos
    0.49
     پرویز
    0.44
    রত্ব
    0.44
     amministrat
    0.44
     pouco
    0.43
    Julian
    0.43
    RoundRect
    0.43
     valamint
    0.42
     ehemal
    0.42
    Act Density 0.000%

    No Known Activations