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

    Neuronpedia

    INDEX
    Explanations

    discussions related to scientific measurements and predictions

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

    fluctuate, increase, or decrease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.54
     autorytatywna
    -0.39
    Unfinished
    -0.37
     tires
    -0.36
    TagMode
    -0.34
    yong
    -0.33
     Allein
    -0.33
     tire
    -0.32
    fo
    -0.32
     sleeves
    -0.32
    POSITIVE LOGITS
     fluctuate
    0.91
     decrease
    0.91
     fluctu
    0.87
     decreased
    0.84
     decreases
    0.82
     plumme
    0.81
     rises
    0.81
     lowered
    0.77
     baisse
    0.77
     decreasing
    0.77
    Act Density 0.255%

    No Known Activations