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

    Neuronpedia

    INDEX
    Explanations

    as a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oit
    0.54
    oct
    0.49
    revoke
    0.48
     आणि
    0.45
     पढ
    0.45
     显示
    0.45
    ions
    0.44
     বিপরীত
    0.44
    iliate
    0.44
     forfeit
    0.43
    POSITIVE LOGITS
    ك
    0.50
    الص
    0.49
     gelegen
    0.49
     weder
    0.48
     của
    0.46
     gewonnen
    0.46
     znalaz
    0.46
    ة
    0.46
     ricevuto
    0.46
    الات
    0.45
    Act Density 0.050%

    No Known Activations