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

    Neuronpedia

    INDEX
    Explanations

    markup or formatting elements commonly used in digital text

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

    HTML formatting tags

    np_acts-logits-general · gemini-2.0-flash

    code comments and html tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.82
    DockStyle
    -0.73
     betweenstory
    -0.72
     queſta
    -0.71
    SafeAreaView
    -0.70
    endregion
    -0.68
    ientras
    -0.67
    parsedMessage
    -0.66
     
    -0.66
     NavController
    -0.66
    POSITIVE LOGITS
    <i>
    1.49
    <em>
    1.40
    /*
    0.84
    <u>
    0.75
    </i>
    0.73
    __(/*!
    0.70
    《
    0.66
    </em>
    0.65
    italic
    0.60
    /*
    0.60
    Act Density 0.164%

    No Known Activations