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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods

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

    file types or domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.60
     whoſe
    -0.53
    AlterField
    -0.51
    原始内容存档于
    -0.51
     leaſt
    -0.50
     anſ
    -0.50
     ſeveral
    -0.50
     juſ
    -0.50
     myſelf
    -0.49
     ſur
    -0.48
    POSITIVE LOGITS
    +'.
    0.49
    .='
    0.47
    .
    0.46
    ..\
    0.45
    piel
    0.44
    ..\..\
    0.43
    \.
    0.43
    componentDid
    0.43
    bricht
    0.42
    oides
    0.42
    Act Density 0.002%

    No Known Activations