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

    Neuronpedia

    INDEX
    Explanations

    lists and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kish
    0.42
     равномер
    0.41
     ওঁ
    0.40
     Talent
    0.40
    ధం
    0.39
     copious
    0.39
     бе
    0.39
     deployed
    0.39
     dispatched
    0.39
     مذا
    0.38
    POSITIVE LOGITS
    ្នក
    0.40
    ..'
    0.40
    >|</
    0.39
    सपने
    0.38
    櫃
    0.37
    咾
    0.37
     comparison
    0.37
    HILL
    0.37
     archiv
    0.36
     integrado
    0.36
    Act Density 0.002%

    No Known Activations