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

    Neuronpedia

    INDEX
    Explanations

    statements indicating simplicity or ease of action

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

    ease and triviality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cardiaque
    -0.49
     fourrure
    -0.47
    IActionResult
    -0.46
     respeito
    -0.46
     duração
    -0.45
     elä
    -0.45
     głos
    -0.42
     motocicletas
    -0.41
     szolg
    -0.41
     sepenuhnya
    -0.41
    POSITIVE LOGITS
     easy
    1.08
    easy
    1.07
    Easy
    1.04
     Easy
    1.03
    easily
    0.96
     Easily
    0.94
     EASY
    0.94
    Easily
    0.94
     easily
    0.93
     eas
    0.81
    Act Density 0.034%

    No Known Activations