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

    Neuronpedia

    INDEX
    Explanations

    whether its

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     أيضا
    0.82
     extérieures
    0.78
    Carte
    0.76
    Giá
    0.75
    ilité
    0.74
    𝕌
    0.73
    Prices
    0.73
    Rustic
    0.72
    簑
    0.72
    Ⲁ
    0.71
    POSITIVE LOGITS
     Вы
    0.78
     Lage
    0.77
     ejecutar
    0.72
     Sh
    0.72
     gosh
    0.72
    iak
    0.71
    iende
    0.71
     sagen
    0.71
     VU
    0.71
     L
    0.70
    Act Density 0.001%

    No Known Activations