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

    Neuronpedia

    INDEX
    Explanations

    defines linguistic types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sonrisa
    0.51
    +
    0.48
    じて
    0.47
     dated
    0.47
    (
    0.46
    Dated
    0.45
    लीय
    0.45
     untuk
    0.44
    Date
    0.43
     коллек
    0.43
    POSITIVE LOGITS
     popupButton
    0.55
     Gallows
    0.54
     ዘዴ
    0.51
     precept
    0.49
     طريقه
    0.48
     आतंकवाद
    0.47
    ämme
    0.46
     Propaganda
    0.46
     標準
    0.46
     النوع
    0.45
    Act Density 0.000%

    No Known Activations