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

    Neuronpedia

    INDEX
    Explanations

    technical writing, where objective descriptions are given and requirements are discussed ("need for", "problem in")

    oai_token-act-pair · gemini-2.0-flash

    serve

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.91
    TintMode
    -0.65
    tagHelperRunner
    -0.64
     AssemblyTitle
    -0.61
     Lightboxes
    -0.59
    ########.
    -0.58
     ComVisible
    -0.57
     Roskov
    -0.57
     дописавши
    -0.56
    Rujuakan
    -0.55
    POSITIVE LOGITS
    javac
    0.46
    buh
    0.45
     glasses
    0.43
    onka
    0.43
     dye
    0.41
    σιμοποι
    0.41
    SALT
    0.41
    MRP
    0.40
     shi
    0.40
    Denne
    0.40
    Act Density 7.125%

    No Known Activations