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

    Neuronpedia

    INDEX
    Explanations

    how to discuss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )
    0.57
    ،
    0.50
    ות
    0.49
    ás
    0.49
    ämä
    0.48
    ي
    0.48
    ﻄ
    0.47
    '
    0.45
    금
    0.45
    ája
    0.45
    POSITIVE LOGITS
     gauze
    0.61
     बेटी
    0.54
     regimens
    0.52
    fireFlower
    0.51
     soddis
    0.50
     toothpaste
    0.49
     使っ
    0.49
     marinade
    0.49
     reciting
    0.49
     प्रतियोग
    0.48
    Act Density 0.000%

    No Known Activations