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

    Neuronpedia

    INDEX
    Explanations

    global + entity type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    1.66
    ९
    1.16
     vélo
    1.11
     તો
    1.09
    ли
    1.09
    ла
    1.09
    ні
    1.04
    ları
    1.04
    >$
    1.04
    泺
    1.04
    POSITIVE LOGITS
    𝑻
    1.08
    ل
    0.99
    𝑒
    0.96
    деся
    0.95
    DAD
    0.95
    ักษณะ
    0.95
     goble
    0.95
     Baill
    0.93
     instigated
    0.93
    د
    0.93
    Act Density 0.018%

    No Known Activations