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

    Neuronpedia

    INDEX
    Explanations

    special character sequences and formatting indicators within text

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

    special characters and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    elemField
    -0.66
    AnimationsModule
    -0.63
    featureID
    -0.62
    IsMutable
    -0.62
    Spoljašnje
    -0.61
     typelib
    -0.60
     propOrder
    -0.60
    Geplaatst
    -0.57
     beginnetje
    -0.57
    ագրություններ
    -0.57
    POSITIVE LOGITS
    <_>
    0.38
    
    0.35
    subpackage
    0.33
     EconPapers
    0.33
     createState
    0.32
    instancetype
    0.32
    0.31
    <bos>
    0.31
    InstanceState
    0.31
    listings
    0.30
    Act Density 0.003%

    No Known Activations