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

    Neuronpedia

    INDEX
    Explanations

    variable name assignment or placeholder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.53
     which
    0.48
    0.47
     Korean
    0.44
     a
    0.43
     the
    0.43
     American
    0.40
     olan
    0.40
    ↵
    0.40
     Copyright
    0.40
    POSITIVE LOGITS
    ллі
    0.44
    Bechyné
    0.43
    לו
    0.40
     גם
    0.39
     கெல்
    0.39
     Еўро
    0.39
     فولت
    0.39
    Geschichte
    0.38
     Володи
    0.38
    תיים
    0.38
    Act Density 0.286%

    No Known Activations