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
    pped
    0.37
     -
    0.34
    el
    0.32
    udy
    0.32
     -"
    0.32
    aloo
    0.31
    etan
    0.31
    >∕
    0.31
    ud
    0.30
    ceptive
    0.29
    POSITIVE LOGITS
    ات
    0.58
    是
    0.50
    在
    0.50
    ও
    0.47
    ة
    0.47
    t
    0.46
    في
    0.46
    도
    0.45
    고
    0.41
    로
    0.40
    Act Density 0.085%

    No Known Activations