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

    Neuronpedia

    INDEX
    Explanations

    listing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aren
    0.48
     is
    0.45
    ys
    0.43
    ’
    0.43
    ని
    0.41
    ik
    0.41
    е
    0.41
    OC
    0.40
     s
    0.40
     沒有
    0.40
    POSITIVE LOGITS
    ן
    0.56
    n
    0.52
    बॉल
    0.50
    ul
    0.49
    ﺘ
    0.48
    ल
    0.48
    정
    0.48
    ０
    0.47
    प
    0.47
    ް
    0.46
    Act Density 1.624%

    No Known Activations