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

    Neuronpedia

    INDEX
    Explanations

    references to historical figures or events

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

    then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supple
    -0.41
    AutoScaleMode
    -0.40
    Tikang
    -0.39
    buttonBar
    -0.39
    #+#
    -0.39
    хівовано
    -0.38
    arias
    -0.37
     blan
    -0.37
     prossimo
    -0.36
    ParallelGroup
    -0.36
    POSITIVE LOGITS
    當時
    0.75
     damals
    0.70
    当时
    0.69
     damal
    0.67
    当時は
    0.65
    当时的
    0.63
    那时
    0.62
     مشين
    0.60
    那时候
    0.60
    当時
    0.58
    Act Density 0.412%

    No Known Activations