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

    Neuronpedia

    INDEX
    Explanations

    block comments and function definitions in code

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

    Code-related tokens and programming terms

    np_acts-logits-general · gemini-2.0-flash

    programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bitField
    -0.45
    OutOf
    -0.45
     
    -0.40
     for
    -0.40
     createdBy
    -0.39
    for
    -0.39
    <h4>
    -0.37
    #![
    -0.37
     å
    -0.37
     لع
    -0.36
    POSITIVE LOGITS
     CreateTagHelper
    1.05
    AxisAlignment
    0.92
     للمعارف
    0.85
     ddelwed
    0.82
     FontWeight
    0.82
     autorytatywna
    0.81
    <unused74>
    0.77
    <pad>
    0.77
    <unused16>
    0.76
    <unused28>
    0.76
    Act Density 0.032%

    No Known Activations