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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the '@' symbol followed by numbers

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

    documentation tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <eos>
    -0.43
    ↵↵
    -0.38
     Wikiseite
    -0.37
     yapılan
    -0.35
     Vorschriften
    -0.34
    bilirsiniz
    -0.34
     nôtre
    -0.34
     deverá
    -0.34
     Weiterbildung
    -0.33
     umí
    -0.33
    POSITIVE LOGITS
     kasarigan
    1.19
     EconPapers
    0.90
     الحره
    0.90
     $_(
    0.86
     $_[
    0.85
     zwiſchen
    0.82
     كومونز
    0.82
    ロウィン
    0.80
    ſicht
    0.80
     ſehr
    0.79
    Act Density 0.001%

    No Known Activations