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

    Neuronpedia

    INDEX
    Explanations

    explaining how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.15
    c
    1.02
    VA
    0.98
    RAchievement
    0.98
    uah
    0.98
    n
    0.97
    VER
    0.95
     จังหวัด
    0.93
    बाग
    0.90
    KOV
    0.90
    POSITIVE LOGITS
    osci
    0.99
    ه‌ها
    0.93
     zien
    0.91
     toma
    0.90
     CDKN
    0.88
    respuesta
    0.88
    iters
    0.87
     uspe
    0.87
     Hanya
    0.86
    stven
    0.86
    Act Density 0.008%

    No Known Activations