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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks/parenthesis

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric literal tokens—especially decimal/floating‐point numbers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    icc
    -0.07
    담
    -0.07
    ागर
    -0.06
    _EDITOR
    -0.06
     doğru
    -0.06
    ricular
    -0.06
    df
    -0.06
    ucceeded
    -0.06
     himself
    -0.06
    onse
    -0.06
    POSITIVE LOGITS
    >M
    0.07
     "><
    0.06
    ']))
↵
    0.06
     specials
    0.06
    하는
    0.06
     splendid
    0.06
     overcrow
    0.06
     Olympia
    0.06
    UnitOfWork
    0.06
    >");↵↵
    0.06
    Act Density 0.021%

    No Known Activations