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

    Neuronpedia

    INDEX
    Explanations

    mannerisms and key presses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ்ட
    0.66
     छ
    0.64
    ោះ
    0.60
    Online
    0.58
     Online
    0.58
     ਜ
    0.58
     langchain
    0.57
    酗
    0.57
    स्ट
    0.56
     পাঠ
    0.56
    POSITIVE LOGITS
     Warner
    0.68
     ВК
    0.66
    λευ
    0.61
    мер
    0.59
     মহল
    0.58
     superiori
    0.58
    绉
    0.58
     yksi
    0.58
    Neutral
    0.57
     preposition
    0.56
    Act Density 0.079%

    No Known Activations