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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating simplicity and ease of understanding or execution

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

    "easy"

    np_acts-logits-general · gemini-2.0-flash

    easy to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     henkil
    -0.54
     aquilo
    -0.52
    DataMember
    -0.52
     vermelhas
    -0.52
     hodnot
    -0.48
     mList
    -0.47
    pulseira
    -0.47
     tatuagens
    -0.45
    HostException
    -0.45
     capucha
    -0.45
    POSITIVE LOGITS
    Easy
    1.29
     Easy
    1.25
    easy
    1.23
     EASY
    1.17
    EASY
    1.12
     easy
    1.01
    easily
    0.93
    Easily
    0.91
     Easily
    0.91
     Ease
    0.89
    Act Density 0.052%

    No Known Activations