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

    Neuronpedia

    INDEX
    Explanations

    reasons why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    闾
    0.95
    বা
    0.91
     spore
    0.90
    ج
    0.89
    てください
    0.89
     начало
    0.88
     ontwikk
    0.88
     orientado
    0.87
     setae
    0.85
    tiin
    0.83
    POSITIVE LOGITS
    of
    1.62
    al
    1.52
    ed
    1.49
    น
    1.36
    el
    1.34
     as
    1.31
    न
    1.30
    ер
    1.30
    n
    1.23
    ن
    1.23
    Act Density 0.087%

    No Known Activations