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

    Neuronpedia

    INDEX
    Explanations

    bright, smiling girl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    йт
    0.56
    κτή
    0.48
    لت
    0.47
    webtoken
    0.46
    STTS
    0.45
    পিত
    0.45
    aszt
    0.43
    рка
    0.43
    digit
    0.42
    үз
    0.42
    POSITIVE LOGITS
     می‌توان
    0.54
     humming
    0.51
     shopping
    0.47
     Blue
    0.46
     localized
    0.45
     रवि
    0.45
     Не
    0.45
     true
    0.45
     Radiant
    0.45
     thinly
    0.44
    Act Density 0.003%

    No Known Activations