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

    Neuronpedia

    INDEX
    Explanations

    time ago, list, number, string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.57
     시장
    0.54
    ير
    0.52
     месте
    0.52
    կ
    0.52
     тради
    0.52
     жид
    0.50
    ılan
    0.50
     ОС
    0.50
    гон
    0.49
    POSITIVE LOGITS
     turut
    0.49
    show
    0.46
    ez
    0.44
    send
    0.42
     aprecia
    0.42
    register
    0.41
    reg
    0.40
     Form
    0.39
     sak
    0.39
     Rak
    0.39
    Act Density 0.000%

    No Known Activations