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

    Neuronpedia

    INDEX
    Explanations

    kilogram of, if not, while she

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quien
    0.50
     logika
    0.47
     lezione
    0.47
    ㈱
    0.47
     prominently
    0.47
     que
    0.46
     që
    0.46
     seçim
    0.46
     bezpiecze
    0.46
     hebat
    0.46
    POSITIVE LOGITS
    i
    0.58
    t
    0.58
    l
    0.56
    dx
    0.54
    All
    0.52
    Yellow
    0.50
     Maa
    0.48
    er
    0.48
    gget
    0.46
    Jenn
    0.46
    Act Density 0.000%

    No Known Activations