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

    Neuronpedia

    INDEX
    Explanations

    patterns related to whitespace and formatting in code

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

    `this` and `self` keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.71
    adaptiveStyles
    -0.71
     Administrativna
    -0.70
    IUrlHelper
    -0.68
    ۜ
    -0.60
    bastien
    -0.59
    SuspendLayout
    -0.58
    ſelf
    -0.57
     createState
    -0.56
    uxxxx
    -0.54
    POSITIVE LOGITS
    omitempty
    0.36
    ConstraintMaker
    0.36
     dlatego
    0.35
     cielos
    0.35
     calcetines
    0.34
     CanadaChoose
    0.34
    unless
    0.32
    eraard
    0.32
     sonst
    0.32
     nikt
    0.31
    Act Density 0.011%

    No Known Activations