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

    Neuronpedia

    INDEX
    Explanations

    reach out for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사람들이
    0.73
     ولكن
    0.71
     lakini
    0.71
     الذين
    0.70
     insanların
    0.69
     ludzi
    0.68
     kanggo
    0.67
     किंतु
    0.66
     northwestern
    0.65
     però
    0.63
    POSITIVE LOGITS
     এটির
    0.75
    特性
    0.66
    Visible
    0.66
    Its
    0.65
    ES
    0.62
    (!
    0.62
    imshow
    0.62
    Depuis
    0.61
     آئینہ
    0.61
     Sicht
    0.61
    Act Density 0.193%

    No Known Activations