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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performance and potential in both people and contexts

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

    maximum or peak state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lesquelles
    -0.35
    Personensuche
    -0.33
     Tatsache
    -0.32
    AutoresizingMask
    -0.32
    CLOSE
    -0.31
     seleção
    -0.31
    المناصب
    -0.31
     engraçado
    -0.31
     Notwendigkeit
    -0.30
    licação
    -0.30
    POSITIVE LOGITS
     maximale
    0.67
     maximum
    0.66
     maximal
    0.65
    Maximum
    0.63
     Maximum
    0.62
     peak
    0.60
    maximum
    0.60
     fullest
    0.60
    maximal
    0.57
     máxima
    0.57
    Act Density 0.124%

    No Known Activations