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

    Neuronpedia

    INDEX
    Explanations

    language, APIs, and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.51
    っち
    0.45
    黎
    0.44
     Morin
    0.43
    艺
    0.43
    slidesPer
    0.42
     टेक्न
    0.42
     bun
    0.42
     doughnut
    0.42
    ሰራ
    0.41
    POSITIVE LOGITS
     ischemia
    0.52
     libros
    0.51
     ricerche
    0.51
    ages
    0.48
    ujo
    0.48
     reprints
    0.48
    aging
    0.48
     personalmente
    0.47
    .//
    0.47
     ansiedad
    0.47
    Act Density 0.000%

    No Known Activations