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

    Neuronpedia

    INDEX
    Explanations

    mathematical variables and terms

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

    solve for variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.41
    AnimationsModule
    -0.40
    estacks
    -0.37
     propOrder
    -0.37
    Transkript
    -0.36
     croix
    -0.35
    QUADS
    -0.35
    bufio
    -0.35
     vai
    -0.33
    WriteTagHelper
    -0.33
    POSITIVE LOGITS
     pleaſure
    0.57
    AnchorStyles
    0.56
    RectangleBorder
    0.55
     queſta
    0.54
     otomatig
    0.53
     étoit
    0.52
    AddTagHelper
    0.51
     pouvoit
    0.50
    ſelves
    0.48
    ChildScrollView
    0.48
    Act Density 0.353%

    No Known Activations