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

    Neuronpedia

    INDEX
    Explanations

    inequalities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opcode
    -0.09
     JFrame
    -0.08
    opcode
    -0.08
     celebration
    -0.08
     graffiti
    -0.08
     lunettes
    -0.08
     astrolog
    -0.08
     quirky
    -0.08
     swing
    -0.08
     apost
    -0.07
    POSITIVE LOGITS
     monot
    0.10
     estimator
    0.10
     cumulative
    0.10
    _sorted
    0.09
     monoton
    0.09
     estimating
    0.09
     estimates
    0.09
     ચુક
    0.09
    umsum
    0.09
     tapered
    0.09
    Act Density 0.024%

    No Known Activations