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

    Neuronpedia

    INDEX
    Explanations

    closing brackets and parentheses used in code or data structures

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

    closing brackets and braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*
    -0.46
     judiciaire
    -0.44
     Austin
    -0.44
    <h2>
    -0.43
    ucci
    -0.42
    Austin
    -0.42
     Muster
    -0.39
    池
    -0.39
     池
    -0.39
    ↵↵↵
    -0.38
    POSITIVE LOGITS
    ]])
    1.16
    }])
    1.13
    })));
    1.06
    )])
    1.02
    )});
    0.91
    ')))
    0.91
    }))
    0.90
    }))
    0.90
    ())))
    0.87
    ]})
    0.86
    Act Density 0.049%

    No Known Activations