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

    Neuronpedia

    INDEX
    Explanations

    found in or near

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    도로
    0.55
    يو
    0.55
    يم
    0.52
    ياز
    0.52
    يع
    0.51
    يكي
    0.46
     utilisation
    0.46
    武器
    0.45
    كرة
    0.45
     proport
    0.44
    POSITIVE LOGITS
     universities
    0.75
     everywhere
    0.73
     viu
    0.70
     sebagai
    0.70
     prominently
    0.67
    ्लाई
    0.66
     or
    0.65
     kwenye
    0.64
     pada
    0.64
     সর্বত্র
    0.64
    Act Density 0.146%

    No Known Activations