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

    Neuronpedia

    INDEX
    Explanations

    code blocks or structures in programming syntax

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

    closing braces in code or programming structures

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

    `} else` control flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     e
    -0.37
     (
    -0.36
    fct
    -0.35
     &
    -0.35
     y
    -0.34
    ct
    -0.34
    JSON
    -0.33
    !
    -0.33
     volo
    -0.33
    edi
    -0.33
    POSITIVE LOGITS
    AddTagHelper
    0.98
    onViewCreated
    0.94
    :]:
    0.91
     Efq
    0.88
    aarrggbb
    0.85
     GoogleFonts
    0.85
     pinulongan
    0.83
    +#+#
    0.82
    AndEndTag
    0.80
     onCreateView
    0.79
    Act Density 0.026%

    No Known Activations