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

    Neuronpedia

    INDEX
    Explanations

    human

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cheese
    -0.07
     melted
    -0.07
     museums
    -0.06
     garden
    -0.06
     restaurant
    -0.06
    encion
    -0.06
     stands
    -0.06
     sais
    -0.06
     δο
    -0.06
     Statements
    -0.06
    POSITIVE LOGITS
    _SHARE
    0.08
     zav
    0.07
    .ReadToEnd
    0.07
     UNICODE
    0.07
    (crate
    0.06
     Rolling
    0.06
    .Generation
    0.06
     Svg
    0.06
    /span
    0.06
    -svg
    0.06
    Act Density 0.013%

    No Known Activations