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

    Neuronpedia

    INDEX
    Explanations

    classified information or documents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    1.38
    u
    1.27
    ui
    1.16
    .
    1.07
    -
    1.06
    قق
    1.03
    зки
    1.02
    rient
    0.96
    ş
    0.96
    ied
    0.96
    POSITIVE LOGITS
    ك
    1.19
    يح
    1.17
     jedną
    1.15
    you
    1.11
    আপনি
    1.09
     be
    1.07
     don
    1.06
    يق
    1.06
     que
    1.05
    ي
    1.04
    Act Density 0.002%

    No Known Activations