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

    Neuronpedia

    INDEX
    Explanations

    satisfy

    np_max-act · gemini-2.0-flash

    The neuron responds to decimal numbers (floating‐point numerals) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    	temp
    -0.07
     podemos
    -0.07
     worm
    -0.07
    -haired
    -0.07
    명을
    -0.06
    SCAN
    -0.06
     →
    -0.06
     anak
    -0.06
    .moveTo
    -0.06
     hasn
    -0.06
    POSITIVE LOGITS
     afflict
    0.06
    lanması
    0.06
     Oy
    0.06
     moduleId
    0.06
     linestyle
    0.06
     Свят
    0.06
     imb
    0.06
    _ERRORS
    0.06
    ỳ
    0.06
    ABB
    0.06
    Act Density 0.006%

    No Known Activations