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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    states
    -0.06
    Pipeline
    -0.06
    Open
    -0.06
     ولد
    -0.06
    IOC
    -0.06
     ()
    -0.06
    نسان
    -0.06
    状
    -0.06
    nga
    -0.06
     framebuffer
    -0.06
    POSITIVE LOGITS
     $("<
    0.07
    šker
    0.07
     Null
    0.06
    ird
    0.06
    über
    0.06
     참고
    0.06
    diamond
    0.06
    ť
    0.06
    ToProps
    0.06
    makers
    0.06
    Act Density 0.033%

    No Known Activations