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

    Neuronpedia

    INDEX
    Explanations

    storefront

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.91
    i
    1.64
    o
    1.63
    י
    1.55
    ا
    1.37
    ن
    1.26
    ام
    1.25
    in
    1.23
    。
    1.21
    oes
    1.20
    POSITIVE LOGITS
    B
    1.15
    3
    1.13
     avait
    1.09
     avaient
    1.09
     aldı
    1.08
     trei
    1.07
     όχι
    1.05
     ilgi
    1.04
    ３
    1.04
     część
    1.03
    Act Density 0.000%

    No Known Activations