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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    This neuron primarily picks out numeric data—especially statistical figures and scores expressed as numbers or decimals.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     cri
    -0.07
     OBS
    -0.07
     bar
    -0.07
    	ar
    -0.07
     comforting
    -0.07
     Celt
    -0.07
    Ya
    -0.07
     dome
    -0.07
    finity
    -0.07
     aroused
    -0.07
    POSITIVE LOGITS
    生活
    0.06
    loan
    0.06
    index
    0.06
    Planet
    0.06
     ise
    0.06
    Undefined
    0.06
     Neptune
    0.06
     definitions
    0.06
     congest
    0.06
    香蕉
    0.06
    Act Density 0.024%

    No Known Activations