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

    Neuronpedia

    INDEX
    Explanations

    constantly evolving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ለን
    0.46
    SCAN
    0.44
    ны
    0.42
    ल्क
    0.41
    тку
    0.41
    пы
    0.41
    BY
    0.41
    iality
    0.41
    ږئ
    0.40
     комму
    0.40
    POSITIVE LOGITS
     Deportivo
    0.47
     இந்தப்
    0.46
     मातरम
    0.46
     Beyonce
    0.46
     Evening
    0.45
     Marilyn
    0.45
     Contour
    0.45
     Desember
    0.44
     STP
    0.44
     Einführung
    0.44
    Act Density 0.000%

    No Known Activations