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

    Neuronpedia

    INDEX
    Explanations

    connections and conjunctions in sentences

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

    and redeem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wiktionnaire
    -0.39
     lastly
    -0.35
    #+#
    -0.34
    ');?>
    -0.32
    "?
    -0.32
    例文帳に追加
    -0.32
     del
    -0.31
    providedIn
    -0.30
    richTextPanel
    -0.29
     surely
    -0.29
    POSITIVE LOGITS
     improve
    0.63
     protect
    0.60
     avoient
    0.59
    achieve
    0.59
    improve
    0.58
     étoit
    0.58
    protect
    0.57
     käyttää
    0.57
    исленность
    0.57
     prevent
    0.57
    Act Density 0.105%

    No Known Activations