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

    Neuronpedia

    INDEX
    Explanations

    speech or texts being expressed aloud.

    oai_token-act-pair · gemini-2.0-flash

    umbling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     épu
    -0.52
     Chriftian
    -0.52
     martens
    -0.52
     itſelf
    -0.51
    tices
    -0.51
     imago
    -0.51
     surveys
    -0.50
     Monfieur
    -0.50
    rile
    -0.50
     poffible
    -0.50
    POSITIVE LOGITS
     насељу
    0.82
    RTLI
    0.72
    ]")]
    0.71
    WriteTagHelper
    0.70
    Билгалдахарш
    0.69
    Бахар
    0.66
     EconPapers
    0.66
    TagMode
    0.63
    yntaxException
    0.62
    GOTREF
    0.58
    Act Density 1.080%

    No Known Activations