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

    Neuronpedia

    INDEX
    Explanations

    mathematical and logical notation or expressions

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

    mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ery
    -0.43
    onade
    -0.40
     Xia
    -0.39
    ########.
    -0.39
    shutil
    -0.38
     ZZ
    -0.36
     Cumber
    -0.36
     shutil
    -0.36
     wad
    -0.35
    MigrationBuilder
    -0.35
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.94
    最快更新
    0.74
    帖最后由
    0.63
    <caption>
    0.56
     disponibilités
    0.54
     EconPapers
    0.50
     ibunya
    0.50
     tiguan
    0.48
     gavetas
    0.47
     orejas
    0.47
    Act Density 0.026%

    No Known Activations