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

    Neuronpedia

    INDEX
    Explanations

    class definitions and annotations in programming code

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

    programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UserScript
    -0.73
     queſta
    -0.71
    GraphicsUnit
    -0.70
    parsedMessage
    -0.68
    elemField
    -0.66
     &___
    -0.65
     ſche
    -0.62
     MediatR
    -0.61
    bootstrapcdn
    -0.61
    IsContent
    -0.60
    POSITIVE LOGITS
     autorytatywna
    0.52
    SuppressLint
    0.30
    PositiveButton
    0.27
    stwie
    0.26
    >(),
    0.26
     initially
    0.26
      
    0.25
     saveur
    0.25
     Besch
    0.25
    ']").
    0.25
    Act Density 0.001%

    No Known Activations