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

    Neuronpedia

    INDEX
    Explanations

    representation plot

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Источник
    0.61
    磊
    0.60
    uyên
    0.59
    चालित
    0.57
    ila
    0.56
     heng
    0.56
    چم
    0.56
    饵
    0.54
     hung
    0.53
    drawiam
    0.53
    POSITIVE LOGITS
     expressed
    2.13
     representation
    2.12
     Express
    2.12
     Representation
    2.05
     express
    2.03
     representations
    2.03
     Represent
    2.02
    Express
    2.02
    Representation
    2.00
     plot
    1.97
    Act Density 0.579%

    No Known Activations