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

    Neuronpedia

    INDEX
    Explanations

    equations/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ahi
    -0.07
    Comparator
    -0.07
     undef
    -0.06
    .weapon
    -0.06
    _grupo
    -0.06
    esa
    -0.06
    _country
    -0.06
     indifference
    -0.06
    outdir
    -0.06
     mez
    -0.06
    POSITIVE LOGITS
     upward
    0.07
     tiled
    0.06
    Summary
    0.06
     smoothing
    0.06
     dign
    0.06
     Bri
    0.06
     fiery
    0.06
     painted
    0.06
     abducted
    0.06
    corn
    0.06
    Act Density 0.019%

    No Known Activations