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

    Neuronpedia

    INDEX
    Explanations

    generic English text

    np_max-act · gemini-2.0-flash

    This neuron lights up on words that denote boundaries, limits, or endpoints in a narrative.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    flow
    -0.07
     nhiệt
    -0.07
     свид
    -0.06
     Εν
    -0.06
     speeches
    -0.06
    rale
    -0.06
    -*-
    -0.06
    ढ़
    -0.06
    Snake
    -0.06
     testData
    -0.06
    POSITIVE LOGITS
    	find
    0.07
    وند
    0.07
    imiter
    0.07
     Pine
    0.07
    都
    0.07
     Stops
    0.06
     ört
    0.06
    Poss
    0.06
     �
    0.06
     postponed
    0.06
    Act Density 0.211%

    No Known Activations