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

    Neuronpedia

    INDEX
    Explanations

    equations including certain symbols and formatting of math and code.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.04
    UnknownFieldSet
    -0.57
     CYTHON
    -0.52
    InjectAttribute
    -0.50
    ra
    -0.49
    })),
    -0.48
     &&
    -0.47
    ↵
    -0.47
    esez
    -0.46
    Бахар
    -0.46
    POSITIVE LOGITS
     ujednoznacz
    0.88
     mourir
    0.78
    ArgsConstructor
    0.72
     mourut
    0.70
     prêtres
    0.68
     CreateTagHelper
    0.64
    HomeAsUpEnabled
    0.63
     fédé
    0.62
    awaiter
    0.61
     kemenangan
    0.60
    Act Density 2.632%

    No Known Activations