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

    Neuronpedia

    INDEX
    Explanations

    what X does

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ఉంది
    0.52
     ఉన్నాయి
    0.50
     vardı
    0.50
     있습니다
    0.50
     עבור
    0.48
    并将
    0.48
    率は
    0.47
     není
    0.46
     vardır
    0.46
    ობს
    0.45
    POSITIVE LOGITS
     να
    1.91
     să
    1.40
    ที่จะ
    1.21
     to
    1.11
     להיות
    1.05
     أن
    0.96
     ausz
    0.87
    ToBe
    0.85
    ທີ່ຈະ
    0.83
     להת
    0.78
    Act Density 0.034%

    No Known Activations