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

    Neuronpedia

    INDEX
    Explanations

    html lang attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     女性
    0.44
     श्रीम
    0.44
    im
    0.42
    H
    0.42
    ண்ண
    0.41
     మంది
    0.41
    Technology
    0.41
    ܦ
    0.41
    SEO
    0.40
    me
    0.40
    POSITIVE LOGITS
    เข้า
    0.51
     défendre
    0.49
     imprimir
    0.45
     இவற்றை
    0.45
     artículos
    0.44
     asegurar
    0.44
    னா
    0.42
     lésions
    0.42
     proporcional
    0.42
     prints
    0.41
    Act Density 0.001%

    No Known Activations