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

    Neuronpedia

    INDEX
    Explanations

    code syntax, especially in Javascript

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.68
     alternativo
    -0.48
    ahme
    -0.46
    ровании
    -0.45
    amerikanischer
    -0.43
    ่า
    -0.43
    使
    -0.43
    rya
    -0.41
    ful
    -0.41
     conveying
    -0.41
    POSITIVE LOGITS
     насељу
    0.75
    sidemargin
    0.74
    TagMode
    0.65
    0.65
    ⓧ
    0.64
    GEBURTSDATUM
    0.63
    parsedMessage
    0.63
     ویکی‌پدیا
    0.61
    नलिखित
    0.60
    Portale
    0.60
    Act Density 3.632%

    No Known Activations