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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax elements and definitions related to generic types and data structures

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

    start of turn object user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.53
    ContentAsync
    -0.47
    almaz
    -0.40
    CloseOperation
    -0.39
    AndEndTag
    -0.39
    BufferException
    -0.38
    jsonwebtoken
    -0.37
    Carriera
    -0.36
     useAppContext
    -0.36
    BoxShadow
    -0.34
    POSITIVE LOGITS
     Magic
    0.45
     Allot
    0.44
     Window
    0.43
    WriteTagHelper
    0.43
    adeloupe
    0.43
    anyol
    0.43
     Cle
    0.42
     Pep
    0.42
     Ref
    0.41
     Spl
    0.41
    Act Density 0.008%

    No Known Activations