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

    Neuronpedia

    INDEX
    Explanations

    numerically quantified data related to scientific experiments or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers following '1-' or 'to'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Alquiler
    -0.33
     bersama
    -0.31
    templateUrl
    -0.31
     later
    -0.30
    ท
    -0.29
    SourceChecksum
    -0.29
     भी
    -0.27
     too
    -0.27
     který
    -0.27
     Finally
    -0.27
    POSITIVE LOGITS
    RTEX
    0.71
    ﹧
    0.67
     $_-
    0.67
     $_=
    0.66
    wiliwch
    0.64
    <unused79>
    0.63
    <unused52>
    0.63
    <unused68>
    0.63
    [@BOS@]
    0.63
    <unused8>
    0.63
    Act Density 0.057%

    No Known Activations