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

    Neuronpedia

    INDEX
    Explanations

    references to numbered items or lists in technical or structured text

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

    beginning of numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.75
     autorytatywna
    -0.56
    ⓧ
    -0.53
    rlpool
    -0.52
    település
    -0.50
    Портали
    -0.49
    ngdoc
    -0.49
    ksiä
    -0.49
    arakhand
    -0.49
    ziplin
    -0.49
    POSITIVE LOGITS
     isInitialized
    0.41
     viewDidLoad
    0.40
    richTextPanel
    0.38
    *
    0.37
    initializeApp
    0.35
    GOTREF
    0.35
     TextAlign
    0.35
    슴
    0.33
    первых
    0.32
    unfinished
    0.32
    Act Density 0.037%

    No Known Activations