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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships between concepts or phrases

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

    ending in "-ing" after conjunctions

    np_acts-logits-general · gemini-2.0-flash

    listing activities and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     بگ
    -0.61
     sağlar
    -0.57
     secrete
    -0.57
     incomplète
    -0.56
     predominate
    -0.56
     inflate
    -0.55
     localize
    -0.54
    Хьажоргаш
    -0.53
     dissect
    -0.53
     jLabel
    -0.53
    POSITIVE LOGITS
     getting
    1.40
     making
    1.35
     doing
    1.31
     taking
    1.23
     being
    1.23
     having
    1.23
     maintaining
    1.17
     obtaining
    1.15
     finding
    1.14
     picking
    1.13
    Act Density 0.232%

    No Known Activations