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

    Neuronpedia

    INDEX
    Explanations

    references to specific media types and formats in data processing contexts

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

    APPLICATION media types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atlik
    -0.51
     respectivement
    -0.50
     bénéfices
    -0.49
     juos
    -0.48
     posiad
    -0.47
     võimal
    -0.47
     intérêts
    -0.47
     arbej
    -0.47
     regalías
    -0.47
     arbejde
    -0.45
    POSITIVE LOGITS
     EClass
    0.70
    RTSC
    0.64
    setVerticalGroup
    0.57
    sizeCache
    0.57
    aarrggbb
    0.54
    endpush
    0.53
    richTextPanel
    0.48
    POM
    0.47
     <=",
    0.47
    ⓧ
    0.47
    Act Density 0.004%

    No Known Activations