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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming or code structures

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

    code-like brackets and braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.55
     nonUne
    -0.48
    GEBURTSDATUM
    -0.47
     Roskov
    -0.47
     ویکی‌پدی
    -0.47
    iastes
    -0.44
    #+#
    -0.44
    principalColumn
    -0.43
    copus
    -0.43
    arana
    -0.43
    POSITIVE LOGITS
     }
    0.80
    enumi
    0.52
     referenties
    0.51
     }
    0.48
     "}
    0.48
    hline
    0.47
     ]
    0.46
     ''}
    0.46
     };
    0.43
     }\
    0.43
    Act Density 0.002%

    No Known Activations