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

    Neuronpedia

    INDEX
    Explanations

    instances of the term "full" in various contexts

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

    full completion of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    that
    -0.32
    But
    -0.30
     at
    -0.29
     by
    -0.29
     he
    -0.28
    but
    -0.28
    Scientists
    -0.28
     Gegenwart
    -0.28
    for
    -0.27
    they
    -0.27
    POSITIVE LOGITS
     full
    1.01
     volledige
    0.90
    完整的
    0.89
     complete
    0.87
     fully
    0.85
     entire
    0.82
     completos
    0.82
     FULL
    0.80
     Full
    0.80
     vollständige
    0.80
    Act Density 0.017%

    No Known Activations