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

    Neuronpedia

    INDEX
    Explanations

    demonstrating results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    engineering
    -0.07
     programmers
    -0.07
    userData
    -0.07
    _multiply
    -0.07
    (ignore
    -0.07
    _mod
    -0.06
    Awesome
    -0.06
     עו
    -0.06
    윳
    -0.06
     NONE
    -0.06
    POSITIVE LOGITS
    骀
    0.07
     calle
    0.07
    .JTable
    0.07
    .issue
    0.07
    便是
    0.07
    做到
    0.07
    还真是
    0.07
     agenda
    0.07
    _dash
    0.07
    ，↵
    0.07
    Act Density 0.061%

    No Known Activations