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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms related to programming or technical terms

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

    cz sequences and GTK

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Наводи
    -0.47
     Quim
    -0.46
    DebuggerStep
    -0.43
    ️
    -0.43
     Griffin
    -0.42
    Kri
    -0.42
     pipeline
    -0.42
     mał
    -0.42
    Skip
    -0.41
    filepath
    -0.41
    POSITIVE LOGITS
    cz
    2.39
     cz
    1.33
    CZ
    1.21
     CZ
    1.08
    Cz
    1.03
     Cz
    1.01
    cza
    0.85
    czka
    0.77
     kasarigan
    0.69
    zcz
    0.68
    Act Density 0.003%

    No Known Activations