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

    Neuronpedia

    INDEX
    Explanations

    Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Russians
    -0.11
     大唐
    -0.09
     гост
    -0.08
     சக
    -0.08
     பள்ள
    -0.08
     Canadians
    -0.08
     Rhino
    -0.08
     செய்திகள்
    -0.08
     housed
    -0.08
     Dx
    -0.08
    POSITIVE LOGITS
    \'
    0.09
    <span
    0.09
    &nbsp
    0.09
    Alternatively
    0.09
    \[
    0.09
    &apos
    0.09
    \\/
    0.08
     \'
    0.08
    &rsquo
    0.08
    \\
    0.08
    Act Density 2.319%

    No Known Activations