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

    Neuronpedia

    INDEX
    Explanations

    mentions of cleaning agents and processes involving water

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

    water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.57
    colgante
    -0.56
     informée
    -0.51
     fédé
    -0.51
    bildēt
    -0.50
    wapV
    -0.49
     söyl
    -0.48
     ModelExpression
    -0.46
    Jaunes
    -0.46
    alakip
    -0.45
    POSITIVE LOGITS
     water
    0.46
    water
    0.44
    Water
    0.40
    :✨
    0.39
     Scramble
    0.37
    存于互联网档案馆
    0.37
    <bos>
    0.36
     soapy
    0.35
    fest
    0.35
     Osun
    0.35
    Act Density 0.002%

    No Known Activations