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

    Neuronpedia

    INDEX
    Explanations

    benefit or cost streams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    יי
    0.58
     Souls
    0.49
     actors
    0.45
    ת
    0.44
     touched
    0.44
    پاکستان
    0.44
    די
    0.43
    जागरण
    0.43
    िलायंस
    0.43
     tapped
    0.42
    POSITIVE LOGITS
    ель
    0.41
    sender
    0.39
    Drawer
    0.39
     nő
    0.39
     ماں
    0.39
    mailer
    0.39
    niches
    0.38
    cimientos
    0.38
     пресс
    0.38
    SizeType
    0.38
    Act Density 0.000%

    No Known Activations