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

    Neuronpedia

    INDEX
    Explanations

    ajax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unset
    -0.07
    VERY
    -0.07
    _copy
    -0.06
    (Int
    -0.06
     Hwy
    -0.06
     cover
    -0.06
    sty
    -0.06
     saturated
    -0.06
    orneys
    -0.06
    ества
    -0.06
    POSITIVE LOGITS
     ajax
    0.09
     AJAX
    0.08
    0.07
    ajax
    0.07
    /met
    0.07
    0.07
     (!(
    0.06
    0.06
     bois
    0.06
     Ajax
    0.06
    Act Density 0.003%

    No Known Activations