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

    Neuronpedia

    INDEX
    Explanations

    function-related syntax patterns, specifically those involving parentheses and commands

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

    Code syntax: parentheses, brackets, and semicolons

    np_acts-logits-general · gemini-2.0-flash

    closing code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chieben
    -0.54
     high
    -0.51
    toEqual
    -0.50
     real
    -0.49
    zano
    -0.48
     full
    -0.47
    componentDid
    -0.47
     play
    -0.46
    dbo
    -0.46
    lide
    -0.46
    POSITIVE LOGITS
     فريبيس
    1.03
    ())))
    0.86
    "])
    0.85
    "]));
    0.79
    ')));
    0.78
    "]))
    0.77
    RegressionTest
    0.77
    ')))
    0.77
    ))}
    0.76
    })();
    0.74
    Act Density 0.712%

    No Known Activations