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

    Neuronpedia

    INDEX
    Explanations

    various forms of the word "draw" and other related terms that imply creation, calculation, and measurement

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

    calculation, estimation, errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    newtheorem
    -0.45
     كومونز
    -0.39
    tovers
    -0.38
    dbc
    -0.37
    assertj
    -0.36
     *++
    -0.36
     zwier
    -0.35
     RouterModule
    -0.35
    ponses
    -0.34
    スーパー
    -0.34
    POSITIVE LOGITS
    +#+#
    0.54
    ьажоргаш
    0.54
    цездатний
    0.52
     betweenstory
    0.50
    GTCX
    0.49
     Italijanski
    0.49
     Administrativna
    0.48
     kasarigan
    0.47
    évaluateur
    0.47
    乓
    0.47
    Act Density 0.141%

    No Known Activations