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

    Neuronpedia

    INDEX
    Explanations

    list of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    त्मक
    1.65
    SIAN
    1.56
    <?,
    1.49
    Ûn
    1.46
    ll
    1.44
    洴
    1.43
    击
    1.41
    "><!--
    1.40
     суток
    1.39
     Viitattu
    1.38
    POSITIVE LOGITS
     quais
    2.08
     וא
    1.88
     që
    1.88
    ור
    1.84
    اء
    1.78
    ع
    1.73
    すぐに
    1.69
     หลัง
    1.66
     demás
    1.63
     leia
    1.63
    Act Density 0.125%

    No Known Activations