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

    Neuronpedia

    INDEX
    Explanations

    marker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contingency
    -0.07
     scheduling
    -0.07
    796
    -0.07
     Administration
    -0.07
     πά
    -0.07
     Christoph
    -0.07
     admin
    -0.06
     dll
    -0.06
    629
    -0.06
    (pl
    -0.06
    POSITIVE LOGITS
     markers
    0.08
    arker
    0.07
     Parker
    0.07
    Marker
    0.07
     мак
    0.07
     marker
    0.07
    런
    0.07
     зер
    0.06
    ケット
    0.06
    基
    0.06
    Act Density 0.006%

    No Known Activations