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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    code files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AccessFile
    -0.52
    '][]
    -0.49
    ArgumentParser
    -0.48
     [*]
    -0.47
    !("{}",
    -0.46
    gry
    -0.43
    JOR
    -0.43
    iliz
    -0.43
    cstring
    -0.43
     Wor
    -0.42
    POSITIVE LOGITS
     onCreateView
    0.69
     дописавши
    0.63
    IsPostBack
    0.61
     Walkover
    0.59
     vectoriales
    0.57
    émoc
    0.57
    izarse
    0.56
     déput
    0.56
     Audiodateien
    0.56
    migrationBuilder
    0.55
    Act Density 7.169%

    No Known Activations