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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "the."

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

    the superlative or unique thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.36
    Kaieteur
    -0.30
    <_>
    -0.28
    nameof
    -0.28
    PO
    -0.28
     prêtre
    -0.27
     بيها
    -0.27
    Enlaces
    -0.26
     Ganze
    -0.26
    INCREF
    -0.25
    POSITIVE LOGITS
     biggest
    0.67
    ロウィン
    0.65
     largest
    0.64
     exceptionally
    0.64
     toughest
    0.64
     fastest
    0.64
     greatest
    0.63
     deadliest
    0.63
     hardest
    0.63
     widest
    0.63
    Act Density 0.015%

    No Known Activations