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

    Neuronpedia

    INDEX
    Explanations

    data related to statistical values, variables, and their relationships

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

    labels and superscripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⋙
    -0.45
    Mob
    -0.39
     Mob
    -0.39
    offsetof
    -0.38
    })$}
    -0.37
     کش
    -0.36
    __()
    -0.35
    OfWork
    -0.35
     webs
    -0.35
     שוליים
    -0.35
    POSITIVE LOGITS
    webElementXpaths
    0.63
    ViewFeatures
    0.61
    windowFixed
    0.59
     Италијани
    0.58
    NameInMap
    0.51
     الرياضيه
    0.49
    цездатний
    0.49
     Syrie
    0.47
     Biôgrafia
    0.47
     Leinwand
    0.45
    Act Density 0.072%

    No Known Activations