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

    Neuronpedia

    INDEX
    Explanations

    programming language-specific syntax and structure

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

    C++ code, especially class/namespace/testing

    np_acts-logits-general · gemini-2.0-flash

    code constructs and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.69
    enumii
    -0.61
     ***!
    -0.54
    TagMode
    -0.52
    +#+#
    -0.52
     nakalista
    -0.51
    enumi
    -0.51
     "..\..\..\
    -0.51
    <?
    -0.50
    ._.
    -0.50
    POSITIVE LOGITS
    DCHECK
    0.68
    isolate
    0.58
     absl
    0.56
     <>",
    0.54
    liosis
    0.54
     isolate
    0.53
    ForTesting
    0.51
     compositor
    0.51
    absl
    0.50
    blink
    0.50
    Act Density 0.305%

    No Known Activations