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

    Neuronpedia

    INDEX
    Explanations

    computational complexity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     masonry
    -0.09
     renovations
    -0.09
     shafts
    -0.09
    _partner
    -0.08
    _spacing
    -0.08
     renovation
    -0.08
    Clamp
    -0.08
     shaft
    -0.08
    Partner
    -0.08
    丁
    -0.07
    POSITIVE LOGITS
     unary
    0.11
     comput
    0.11
     computational
    0.11
     binary
    0.10
    (binary
    0.10
     Unary
    0.10
    (Binary
    0.10
    Unary
    0.10
     Binary
    0.10
     tract
    0.10
    Act Density 0.006%

    No Known Activations