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

    Neuronpedia

    INDEX
    Explanations

    references to washing or cleansing actions

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

    washing action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.59
    randomUUID
    -0.53
     idéia
    -0.53
     Biele
    -0.52
    UIControlState
    -0.51
    eon
    -0.51
    sizePolicy
    -0.51
     eventId
    -0.51
    fein
    -0.50
    ContentAlignment
    -0.49
    POSITIVE LOGITS
     Wash
    1.17
    Wash
    1.13
     wash
    1.09
     WASH
    1.07
     Washing
    1.04
    Washing
    0.98
     washing
    0.97
    wash
    0.96
     washes
    0.93
     Washburn
    0.93
    Act Density 0.012%

    No Known Activations