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

    Neuronpedia

    INDEX
    Explanations

    open and close parentheses in code snippets

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

    code block start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     build
    -0.52
     Schild
    -0.51
    '">
    -0.49
    ]})
    -0.49
     ""))
    -0.47
    ]')
    -0.45
    servez
    -0.45
    ))->
    -0.44
     Build
    -0.44
    Build
    -0.44
    POSITIVE LOGITS
    (_
    1.94
    (__
    1.20
    >(_
    1.17
     (_
    1.17
    ($_
    1.02
    (@
    1.01
    (___
    0.98
    (!__
    0.96
    [_
    0.95
    ($
    0.93
    Act Density 0.002%

    No Known Activations