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

    Neuronpedia

    INDEX
    Explanations

    code and technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Unhandled
    -0.07
    Trading
    -0.06
    venth
    -0.06
    Ghost
    -0.06
     Division
    -0.06
     अक
    -0.06
     مان
    -0.06
    icle
    -0.06
     reap
    -0.06
     CFO
    -0.06
    POSITIVE LOGITS
     graphql
    0.07
    .edu
    0.07
     sev
    0.06
    Growing
    0.06
    //[
    0.06
     eo
    0.06
    tags
    0.06
    Rotate
    0.06
     demographics
    0.06
    <style
    0.06
    Act Density 0.001%

    No Known Activations