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

    Neuronpedia

    INDEX
    Explanations

    the word "plug".

    oai_token-act-pair · gemini-2.0-flash

    plug

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -1.10
     дописавши
    -1.09
    didSet
    -1.09
     Monfieur
    -1.05
     myſelf
    -1.05
    FTFY
    -1.04
    </tfoot>
    -1.01
     snippetHide
    -1.00
     Reſ
    -0.99
     itſelf
    -0.98
    POSITIVE LOGITS
    -
    0.68
    m
    0.67
    h
    0.65
    l
    0.62
    </i>
    0.61
    p
    0.59
    k
    0.59
    not
    0.59
    f
    0.57
    s
    0.57
    Act Density 1.478%

    No Known Activations