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

    Neuronpedia

    INDEX
    Explanations

    ratelicenseBlueSaludTiber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    న్న
    0.52
     Hutton
    0.44
    ј
    0.44
    특히
    0.43
    हमें
    0.43
    um
    0.42
    bi
    0.42
    amour
    0.41
    羞
    0.41
    在我们
    0.41
    POSITIVE LOGITS
     appliances
    0.46
     ate
    0.44
     cruelty
    0.43
     cells
    0.42
     hardware
    0.42
     بأ
    0.42
     cabinets
    0.42
     winnings
    0.42
     looked
    0.41
     dressings
    0.41
    Act Density 0.080%

    No Known Activations