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

    Neuronpedia

    INDEX
    Explanations

    brand names and specific product mentions

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

    CWE, Umenyiora, Kiwanuka

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.55
     mijne
    -0.50
     Phry
    -0.47
     beroep
    -0.47
     komende
    -0.47
     Chwiliwch
    -0.45
    +#+#
    -0.43
     吋
    -0.43
     giù
    -0.42
     zijne
    -0.42
    POSITIVE LOGITS
     lenker
    0.91
    UserScript
    0.78
    InvalidArgument
    0.67
    Datuak
    0.66
    autogui
    0.53
    TextWatcher
    0.52
     muối
    0.49
    AnchorTagHelper
    0.48
    niająca
    0.47
     Cheyenne
    0.47
    Act Density 0.003%

    No Known Activations