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

    Neuronpedia

    INDEX
    Explanations

    syntax elements or types related to programming and data structure definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    type annotations and function signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enderror
    -0.43
     Digest
    -0.42
     Lear
    -0.42
    readLine
    -0.41
     coloring
    -0.41
    weightedMode
    -0.41
     colouring
    -0.40
    HttpFoundation
    -0.40
     Coment
    -0.39
     Bix
    -0.39
    POSITIVE LOGITS
    Personendaten
    0.53
     مشين
    0.40
    Bibliograf
    0.39
     समीक्षाओं
    0.39
     CanadaChoose
    0.39
    nezeu
    0.38
    BeNil
    0.37
    ༘
    0.37
     MEAN
    0.36
    endmodule
    0.36
    Act Density 0.119%

    No Known Activations