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

    Neuronpedia

    INDEX
    Explanations

    structures or representations of data formats

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

    PHP code assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.52
    thansa
    -0.51
    _',
    -0.50
    WebServlet
    -0.49
     Kruse
    -0.49
    Luxem
    -0.47
    karena
    -0.47
    ':{'
    -0.47
    }/${
    -0.46
    "}>
    -0.46
    POSITIVE LOGITS
    []
    2.27
    []
    1.20
     []
    1.17
    [])
    1.15
    [][]
    1.10
    []"
    1.06
    |[]
    1.02
    []=
    1.01
    [];
    0.99
    [],
    0.98
    Act Density 0.009%

    No Known Activations