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

    Neuronpedia

    INDEX
    Explanations

    code syntax and structural elements related to programming languages

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

    code closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ième
    -0.48
    ;
    -0.46
    y
    -0.45
    sweise
    -0.44
    يًا
    -0.44
    er
    -0.43
    ljiv
    -0.42
    oires
    -0.42
    NameInMap
    -0.42
    iotic
    -0.41
    POSITIVE LOGITS
    <bos>
    0.97
    ]),
    0.81
    "));
    0.80
    }),
    0.77
    ")));
    0.74
    
    0.73
    ]));
    0.72
    "))
    0.71
    )),
    0.71
    ()));
    0.71
    Act Density 0.003%

    No Known Activations