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

    Neuronpedia

    INDEX
    Explanations

    might break tomorrow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irc
    1.18
    arum
    1.10
    cau
    1.09
    wah
    1.08
    uari
    1.07
    磡
    1.06
    얏
    1.02
    subscribed
    1.01
    uset
    1.00
    acetamol
    1.00
    POSITIVE LOGITS
     كل
    1.25
     বাকি
    1.25
     الم
    1.21
    ದುಕೊಳ್ಳ
    1.16
     Blow
    1.14
     ر
    1.14
     لم
    1.14
     ص
    1.12
     يت
    1.07
    Ма
    1.07
    Act Density 0.061%

    No Known Activations