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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the underscore character

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

    variable assignments with underscores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.48
     embaraz
    -0.48
     arşivlendi
    -0.46
     becauſe
    -0.46
    AnchorTagHelper
    -0.45
    ambilan
    -0.45
     quæ
    -0.44
     sige
    -0.44
    itemize
    -0.44
    Decrypt
    -0.44
    POSITIVE LOGITS
     (_.
    1.23
     _.
    1.05
    (_.
    0.98
    _.
    0.84
    <bos>
    0.74
    ._.
    0.66
    $_.
    0.63
    <_>
    0.60
    .$_
    0.58
     -.
    0.57
    Act Density 0.014%

    No Known Activations