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

    Neuronpedia

    INDEX
    Explanations

    error message context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.45
    i
    1.31
    न
    1.28
    ن
    1.23
    ל
    1.23
    ло
    1.16
    ন
    1.16
    OT
    1.14
    ב
    1.13
    ه
    1.09
    POSITIVE LOGITS
    ंकन
    1.16
    žem
    1.13
     ◆
    1.10
    után
    1.09
    ’”
    1.08
    ల్‌
    1.07
    rifice
    1.06
    âge
    1.05
    てください
    1.05
    ัฒ
    1.05
    Act Density 0.190%

    No Known Activations