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

    Neuronpedia

    INDEX
    Explanations

    the string "tmp"

    oai_token-act-pair · gemini-2.0-flash

    tmp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     “
    -0.97
     "
    -0.80
    h
    -0.71
    ch
    -0.71
    g
    -0.68
    l
    -0.66
    ar
    -0.65
    w
    -0.65
    mi
    -0.63
    li
    -0.62
    POSITIVE LOGITS
     Wicidata
    1.13
    tvguidetime
    1.08
    findpost
    1.08
     Shakspeare
    1.05
    BibitemShut
    1.03
     myſelf
    1.03
    setVerticalGroup
    1.02
    IUrlHelper
    1.02
     itſelf
    1.01
    tonode
    0.97
    Act Density 0.757%

    No Known Activations