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

    Neuronpedia

    INDEX
    Explanations

    roman numerals and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ((
    0.95
    ((
    0.88
    ️⃣
    0.86
    ...@
    0.79
     (
    0.73
    ("(
    0.72
    (")
    0.71
    igheden
    0.70
     She
    0.70
    0
    0.70
    POSITIVE LOGITS
     SIX
    0.73
    proved
    0.73
    育成
    0.73
    ￳
    0.70
    зге
    0.68
     આર
    0.68
    完善
    0.67
     partenaires
    0.67
     ठोस
    0.67
    領域
    0.67
    Act Density 0.165%

    No Known Activations