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

    Neuronpedia

    INDEX
    Explanations

    patterns or structures in programming code

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

    Code snippets with brackets or braces

    np_acts-logits-general · gemini-2.0-flash

    closing code blocks or tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    %;
    -0.75
    accia
    -0.62
     off
    -0.60
    ORTS
    -0.60
    <>
    -0.60
    WebServlet
    -0.56
     con
    -0.56
    ():
    -0.55
     =
    -0.54
     mit
    -0.54
    POSITIVE LOGITS
    }
    1.51
    )
    1.08
    </
    1.07
    ]
    1.01
    };
    0.93
    }
    0.91
    }.
    0.89
    })
    0.88
    </tr>
    0.87
    """
    0.86
    Act Density 0.047%

    No Known Activations