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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting elements used in mathematical expressions or code

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

    Numbers appearing mid-text

    np_acts-logits-general · gemini-2.0-flash

    content and context anchors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.52
    omores
    -0.50
    @[+][
    -0.46
    oredCriteria
    -0.46
    nolia
    -0.45
     corrid
    -0.43
    HttpPut
    -0.42
    wegg
    -0.42
    ㅐ
    -0.42
    า
    -0.42
    POSITIVE LOGITS
    ContentAsync
    0.92
    rungsseite
    0.71
    IsContent
    0.67
    الحياه
    0.65
    UserScript
    0.61
    MLLoader
    0.60
    AddTagHelper
    0.60
    WebControls
    0.59
    ⓧ
    0.59
    下载附件
    0.59
    Act Density 0.316%

    No Known Activations