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

    Neuronpedia

    INDEX
    Explanations

    words related to coding with occasional bursts for list-like and menu-related words.

    oai_token-act-pair · gemini-2.0-flash

    say "."

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.50
    switch
    -0.47
    med
    -0.47
     Chwiliwch
    -0.46
    bar
    -0.44
    ();)
    -0.44
    createClass
    -0.43
    Med
    -0.43
     Med
    -0.42
    dAtA
    -0.42
    POSITIVE LOGITS
    ChildScrollView
    0.82
     resourceCulture
    0.80
    ArrowToggle
    0.71
    writeFieldEnd
    0.71
    AsUp
    0.68
    bibinfo
    0.67
    fjspx
    0.66
    ViewImports
    0.65
    estacks
    0.65
     externi
    0.64
    Act Density 2.277%

    No Known Activations