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

    Neuronpedia

    INDEX
    Explanations

    apostrophes and their surrounding words.

    oai_token-act-pair · gemini-2.0-flash

    apostrophes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     referenties
    -0.56
     kasarigan
    -0.56
    culable
    -0.55
    cency
    -0.50
    fated
    -0.49
    зулта
    -0.49
    */,
    -0.47
    PathVariable
    -0.45
    Hiya
    -0.45
     **)
    -0.44
    POSITIVE LOGITS
    <bos>
    0.75
     étoient
    0.53
     avoient
    0.50
     vérit
    0.45
     NDEBUG
    0.44
    issenschaft
    0.44
    voorbeeld
    0.42
     odeur
    0.42
     étoit
    0.41
     itſelf
    0.41
    Act Density 11.106%

    No Known Activations