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

    Neuronpedia

    INDEX
    Explanations

    code diffs and additions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    omyosin
    0.32
    compression
    0.31
    orbent
    0.30
    埬
    0.30
    ेयर
    0.30
    semos
    0.30
    RESSION
    0.29
    autista
    0.29
    asitriangular
    0.29
    compressible
    0.28
    POSITIVE LOGITS
     Diff
    0.30
    @@
    0.29
    diff
    0.29
     None
    0.28
     type
    0.28
     row
    0.28
     הכ
    0.27
     diff
    0.27
    ToString
    0.27
    Diff
    0.27
    Act Density 0.000%

    No Known Activations