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

    Neuronpedia

    INDEX
    Explanations

    variable declarations and types in programming code

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

    programming syntax and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.84
     Италијани
    -0.63
     snippetHide
    -0.60
    ьаж
    -0.60
     Administrativna
    -0.59
     Taktlose
    -0.57
    mobileqq
    -0.55
    TagMode
    -0.54
     tiguan
    -0.54
    webElementXpaths
    -0.53
    POSITIVE LOGITS
    ValueGenerated
    0.41
    MLLoader
    0.38
    CloseOperation
    0.37
    LabelTagHelper
    0.35
    DockStyle
    0.34
     BrowserModule
    0.33
    spher
    0.31
     visuel
    0.30
     track
    0.30
     tracks
    0.30
    Act Density 0.046%

    No Known Activations