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

    Neuronpedia

    INDEX
    Explanations

    technical computing

    np_max-act · gemini-2.0-flash

    Python code snippets and examples related to data visualization with specific libraries.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects floating-point numeric literals (decimal numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    าห
    -0.07
    代理
    -0.06
    ominated
    -0.06
     یافته
    -0.06
    But
    -0.06
     एस
    -0.06
    来说
    -0.06
    _REUSE
    -0.06
     kont
    -0.06
    .Success
    -0.06
    POSITIVE LOGITS
     cornerback
    0.07
     Throwable
    0.07
     CNN
    0.07
    '^$',
    0.07
    Selection
    0.07
    快
    0.06
    horizontal
    0.06
    ヌ
    0.06
    緒
    0.06
    lapping
    0.06
    Act Density 0.006%

    No Known Activations