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

    Neuronpedia

    INDEX
    Explanations

    indicators of success and affirmation in contexts of achievement

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

    testaments to something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    院
    -0.45
    หวัด
    -0.42
     تانيه
    -0.42
     Dummy
    -0.41
    Dummy
    -0.41
     Relief
    -0.40
     dummy
    -0.39
     Favorites
    -0.39
    SSH
    -0.38
    少
    -0.38
    POSITIVE LOGITS
     disambiguazione
    0.52
     propOrder
    0.46
     autorytatywna
    0.43
    setVerticalGroup
    0.43
    toBeTruthy
    0.42
     great
    0.42
     Menschheit
    0.42
     насколько
    0.41
     sentimenti
    0.41
     how
    0.41
    Act Density 0.038%

    No Known Activations