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

    Neuronpedia

    INDEX
    Explanations

    TIME, show, services, ADMIN value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.45
    ла
    0.38
    কে
    0.31
    र्
    0.31
    지
    0.30
    sthe
    0.30
    ει
    0.29
     $"{
    0.29
    ना
    0.29
     Azərbaycan
    0.29
    POSITIVE LOGITS
    and
    0.48
     and
    0.45
    0
    0.30
    মতী
    0.30
    elling
    0.29
    aine
    0.29
    _
    0.29
    ０
    0.29
     to
    0.29
     fonti
    0.27
    Act Density 0.046%

    No Known Activations