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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.09
    ️⃣
    1.04
    د
    1.00
    OP
    0.97
    ⃣
    0.96
    ت
    0.93
    ۰
    0.93
    ৪১
    0.93
    ৩৫
    0.92
    ৪২
    0.90
    POSITIVE LOGITS
    fold
    1.16
    ième
    1.08
    жды
    1.08
    pence
    1.06
    fifths
    1.02
    dimensionality
    1.01
     dimensionality
    0.95
     livraison
    0.94
     separate
    0.94
     दिवसीय
    0.92
    Act Density 0.121%

    No Known Activations