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

    Neuronpedia

    INDEX
    Explanations

    health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .capitalize
    -0.07
    Im
    -0.07
    arsity
    -0.06
     Sensor
    -0.06
    .peek
    -0.06
    istik
    -0.06
     مما
    -0.06
    oothing
    -0.06
     От
    -0.06
    _tra
    -0.06
    POSITIVE LOGITS
     biggest
    0.08
    .onOptionsItemSelected
    0.07
    */
↵
    0.06
    akening
    0.06
    liquid
    0.06
    خانه
    0.06
     GetById
    0.06
     Glam
    0.06
    cripts
    0.06
     hiring
    0.06
    Act Density 0.001%

    No Known Activations