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

    Neuronpedia

    INDEX
    Explanations

    references to films and filmmaking

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

    stories and narratives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.66
     geslacht
    -0.66
     pitié
    -0.61
    EDEFAULT
    -0.60
     unsuccessful
    -0.58
    gister
    -0.58
    WriteBarrier
    -0.57
     vulgaires
    -0.57
    waitKey
    -0.57
    ellschaft
    -0.57
    POSITIVE LOGITS
    お楽しみに
    0.54
     audience
    0.49
    自分
    0.49
     exciting
    0.48
    windowFixed
    0.47
     opener
    0.47
    TagHelper
    0.47
    exc
    0.46
     character
    0.46
     montañas
    0.46
    Act Density 0.091%

    No Known Activations