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

    Neuronpedia

    INDEX
    Explanations

    non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    k
    0.51
    et
    0.49
    ण्यासाठी
    0.48
    y
    0.48
    on
    0.48
    pessoas
    0.48
     طریقے
    0.46
     ادارے
    0.44
    써
    0.42
    واں
    0.41
    POSITIVE LOGITS
    0.48
    জ
    0.45
    েনা
    0.44
     НЕ
    0.44
    ја
    0.44
    મ
    0.42
     นั่น
    0.40
    ة
    0.40
     которую
    0.39
    нику
    0.39
    Act Density 0.110%

    No Known Activations