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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate types, characteristics, or classifications of items or concepts

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

    followed by articles or prepositions

    np_acts-logits-general · gemini-2.0-flash

    asking "what" or "which"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.56
    Пото
    -0.33
     kram
    -0.31
    .
    -0.30
    condu
    -0.30
    hau
    -0.29
    进
    -0.29
    bebasan
    -0.29
     пото
    -0.28
    setAlignment
    -0.28
    POSITIVE LOGITS
    Хьажоргаш
    0.63
    出版年
    0.63
     estekak
    0.60
    новниш
    0.57
     linkovi
    0.56
     Efq
    0.56
    Hochspringen
    0.55
     JpaRepository
    0.54
    Folgende
    0.54
     autorytatywna
    0.53
    Act Density 0.207%

    No Known Activations