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

    Neuronpedia

    INDEX
    Explanations

    sections of text that provide detailed explanations or analyses

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

    and then explain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Dun
    -0.42
    AddTagHelper
    -0.42
     Wikimedijinoj
    -0.40
     riot
    -0.39
     dun
    -0.39
     Hon
    -0.39
     Pri
    -0.38
    Jîn
    -0.37
     Autorisations
    -0.37
    Pwd
    -0.37
    POSITIVE LOGITS
    CppMethod
    0.63
    IntoConstraints
    0.61
    inSlope
    0.59
    IContainer
    0.58
    Rptr
    0.58
    ChildScrollView
    0.57
    Diweddarwch
    0.56
    transQ
    0.53
     wikipagina
    0.52
     queſta
    0.51
    Act Density 0.574%

    No Known Activations