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

    Neuronpedia

    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash

    The neuron flags numeric literal tokens (e.g. integers or floating-point numbers) in the input.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Run
    -0.07
     commune
    -0.07
    IMENT
    -0.07
    发行
    -0.07
     Core
    -0.06
    토
    -0.06
    Trip
    -0.06
     Cu
    -0.06
    ordinate
    -0.06
    nad
    -0.06
    POSITIVE LOGITS
     spíše
    0.06
    かい
    0.06
    	inst
    0.06
    кової
    0.06
    ikipedia
    0.06
    	back
    0.06
    αρά
    0.06
    .toCharArray
    0.06
    /el
    0.06
     onMouse
    0.06
    Act Density 0.025%

    No Known Activations