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

    Neuronpedia

    INDEX
    Explanations

    the character "t" after a sequence of digits and underscores

    oai_token-act-pair · gemini-2.0-flash

    t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     greateſt
    -0.67
     Jefus
    -0.67
     Hift
    -0.66
    EFIAPI
    -0.65
    umbersome
    -0.65
    CONCLUS
    -0.64
     vectorstock
    -0.64
     Theſe
    -0.63
     Diſ
    -0.63
     réguli
    -0.62
    POSITIVE LOGITS
    <bos>
    2.48
    '
    0.73
    “
    0.65
     the
    0.65
    ’
    0.65
    -
    0.64
    "
    0.64
     and
    0.62
    [
    0.60
     it
    0.59
    Act Density 0.110%

    No Known Activations