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

    Neuronpedia

    INDEX
    Explanations

    question prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isz
    0.46
     of
    0.46
    حث
    0.44
    zyk
    0.44
     discussed
    0.44
     шуда
    0.44
     Áng
    0.43
     Bankr
    0.42
    OfString
    0.42
     strategi
    0.42
    POSITIVE LOGITS
    ﻞ
    0.57
    ל
    0.54
     ಇದಕ್ಕೆ
    0.53
    u
    0.52
     करो
    0.52
     ພວກເຮົາ
    0.52
     यासाठी
    0.51
     lancio
    0.51
     entonces
    0.50
    啦
    0.50
    Act Density 0.001%

    No Known Activations