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

    Neuronpedia

    INDEX
    Explanations

    Handles basic structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CategoryImage
    0.61
     vaksin
    0.52
     ाट
    0.52
     zakład
    0.51
     theologians
    0.49
     peralatan
    0.49
     exposición
    0.48
     komunikasi
    0.48
     görünt
    0.47
     कमाई
    0.47
    POSITIVE LOGITS
    型
    0.46
     سواء
    0.45
    ĩ
    0.44
     hydrocarbon
    0.41
     locked
    0.41
    是否
    0.41
    نوع
    0.41
    -
    0.41
    自分
    0.40
    icient
    0.40
    Act Density 0.003%

    No Known Activations