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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric measurement values, especially decimal numbers in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     editors
    -0.06
     discs
    -0.06
     deposited
    -0.06
     examination
    -0.06
     rundown
    -0.06
    encryption
    -0.06
     cooperate
    -0.05
    ov
    -0.05
     oceans
    -0.05
    eneration
    -0.05
    POSITIVE LOGITS
    APIView
    0.08
    (Direction
    0.07
    详情
    0.07
     köy
    0.07
     ActionBar
    0.07
     дити
    0.07
    IntegerField
    0.06
     günü
    0.06
     Craigslist
    0.06
    ……………………
    0.06
    Act Density 0.059%

    No Known Activations