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

    Neuronpedia

    INDEX
    Explanations

    application vs foundational research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PHOTOS
    0.46
    BU
    0.45
    Zone
    0.44
    Programme
    0.44
    Panel
    0.44
    MO
    0.43
    Prefix
    0.43
    Front
    0.43
    Car
    0.42
    Según
    0.42
    POSITIVE LOGITS
     tutto
    0.49
     มาก
    0.49
    lepiej
    0.48
     লাফ
    0.46
     ആശ
    0.45
     ٹھ
    0.45
     tudo
    0.45
     குற
    0.44
     کیس
    0.44
    วย
    0.44
    Act Density 0.003%

    No Known Activations