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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and outputs related to games and arrays

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

    programming data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.62
    
    -0.59
    CloseOperation
    -0.57
    InteropServices
    -0.54
    niſſe
    -0.52
     FetchType
    -0.51
     CiNii
    -0.50
     désolés
    -0.50
    __':
    -0.49
    \{\\
    -0.49
    POSITIVE LOGITS
    rouvez
    0.39
    ammer
    0.39
    <eos>
    0.36
     Vorg
    0.35
     pinulongan
    0.35
     기
    0.35
    amante
    0.35
    kmäler
    0.34
    的情
    0.34
     favorece
    0.34
    Act Density 0.037%

    No Known Activations