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

    Neuronpedia

    INDEX
    Explanations

    beyond Husserl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    €™
    0.75
    ancji
    0.72
    खिक
    0.71
    ..--
    0.69
     cuello
    0.68
    \/}
    0.68
     ciekaw
    0.68
     отказаться
    0.67
     चाहे
    0.66
     lograr
    0.65
    POSITIVE LOGITS
     barometer
    0.82
    綱
    0.81
     screenshot
    0.78
     ATA
    0.73
     equated
    0.73
    ដែលអាច
    0.73
     TÜ
    0.72
    АТ
    0.71
     framebuffer
    0.71
     feud
    0.71
    Act Density 0.003%

    No Known Activations