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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with different categories or classes

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

    HTML / UI elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.63
     Accesat
    -0.48
    脚注の使い方
    -0.46
    GraphicsUnit
    -0.42
     protoimpl
    -0.42
     trajets
    -0.39
    kmäler
    -0.39
    commune
    -0.39
    DOCTYPE
    -0.39
     跳转至
    -0.37
    POSITIVE LOGITS
    SequentialGroup
    0.63
    reactstrap
    0.56
     AssemblyTitle
    0.55
    AnchorStyles
    0.52
    ParallelGroup
    0.50
    HtmlAttribute
    0.50
     jButton
    0.46
    ToLeft
    0.44
    IBarButtonItem
    0.44
    webElementXpaths
    0.43
    Act Density 0.001%

    No Known Activations