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

    Neuronpedia

    INDEX
    Explanations

    sections that contain introductory or context-setting phrases, particularly indicating the start of a discussion or discourse

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

    Tokens followed by numbers or symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers and special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -1.06
     estekak
    -0.90
    webElementXpaths
    -0.84
    LookAnd
    -0.83
    IndentedString
    -0.78
     defaultstate
    -0.76
    WebVitals
    -0.76
     CreateTagHelper
    -0.72
    RegressionTest
    -0.70
    XMLSchema
    -0.69
    POSITIVE LOGITS
    EnableWeb
    0.57
    "]));
    0.50
    inheritDoc
    0.48
    뮬
    0.45
     LSA
    0.44
    ”?
    0.42
    </u>
    0.42
    <0xDA>
    0.42
    %\]
    0.42
     Majefty
    0.42
    Act Density 0.030%

    No Known Activations