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

    Neuronpedia

    INDEX
    Explanations

    CVE or VSC identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    är
    1.10
     که
    1.10
    ری
    1.09
    to
    1.05
    רי
    1.05
    که
    1.03
    ח
    1.01
     sprawd
    1.00
     времени
    0.98
     şark
    0.98
    POSITIVE LOGITS
    ر
    1.27
    س
    1.26
    ovou
    1.23
    un
    1.20
    ot
    1.08
    s
    1.07
    ος
    1.04
    و
    1.04
    ుల
    1.02
    ských
    1.02
    Act Density 0.000%

    No Known Activations