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

    Neuronpedia

    INDEX
    Explanations

    division and arithmetic expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    segaretro
    0.41
    १८४
    0.39
    Gosudarstvennyj
    0.39
    rüstung
    0.39
    lumat
    0.38
    齙
    0.38
    forderung
    0.38
    lardı
    0.38
    üğünüz
    0.37
    क्रीम
    0.37
    POSITIVE LOGITS
     x
    0.40
     C
    0.39
     b
    0.38
    -
    0.38
     but
    0.37
     +
    0.36
    ,
    0.36
     t
    0.36
     triangle
    0.36
     Decor
    0.36
    Act Density 0.201%

    No Known Activations