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

    Neuronpedia

    INDEX
    Explanations

    code snippets including variable names, especially related to memory management, HTTP, and other system-level objects

    oai_token-act-pair · gemini-2.0-flash

    m

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mässig
    -0.47
    ölkerung
    -0.46
    GraphicsUnit
    -0.45
    RTEE
    -0.44
     ddelweddau
    -0.44
     mag
    -0.44
     мәкал
    -0.43
     typelib
    -0.42
    новниш
    -0.41
     OFDb
    -0.41
    POSITIVE LOGITS
     nahilalakip
    0.59
    GIH
    0.59
    FOOTNOTES
    0.57
    viewDidLoad
    0.57
    kn
    0.54
    uitton
    0.54
    ioutil
    0.53
    kowania
    0.53
    setViewportView
    0.53
    stdio
    0.52
    Act Density 16.876%

    No Known Activations