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

    Neuronpedia

    INDEX
    Explanations

    code/instructions

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numbers (decimal values) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Rod
    -0.08
    etections
    -0.07
    (in
    -0.07
    (level
    -0.07
    _PR
    -0.07
    モ
    -0.07
    Stride
    -0.06
    족
    -0.06
    _IN
    -0.06
     POST
    -0.06
    POSITIVE LOGITS
    alnız
    0.07
    ».↵↵
    0.07
    ?'↵↵
    0.07
     capt
    0.06
     '#
    0.06
    š
    0.06
    >I
    0.06
     тяжел
    0.06
     ">
    0.06
    ?>"
    0.06
    Act Density 0.002%

    No Known Activations