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

    Neuronpedia

    INDEX
    Explanations

    content outlines and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    оти
    0.40
    otide
    0.38
    dare
    0.38
    ত্ব
    0.38
    Oro
    0.38
    ocity
    0.37
     حفظ
    0.37
    Pere
    0.36
    Pis
    0.36
    داد
    0.36
    POSITIVE LOGITS
     اف
    0.61
     افز
    0.58
     af
    0.49
    zar
    0.49
    జర్
    0.47
     أف
    0.45
    اندی
    0.43
     zar
    0.42
     Zar
    0.42
    ियर
    0.41
    Act Density 0.009%

    No Known Activations