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

    Neuronpedia

    INDEX
    Explanations

    liquid

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on mentions of liquid‐filled or fluid‐containing chambers or passages in technical patent descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Mill
    -0.07
    701
    -0.07
     tiện
    -0.06
     contestants
    -0.06
    mall
    -0.06
     Lois
    -0.06
     sonrasında
    -0.06
     hypotheses
    -0.06
    Prod
    -0.06
    efd
    -0.06
    POSITIVE LOGITS
    EncodingException
    0.07
    expanded
    0.06
    'être
    0.06
     baff
    0.06
     June
    0.06
    Fresh
    0.06
     inserts
    0.06
    .Dictionary
    0.06
    .INFO
    0.06
     accur
    0.06
    Act Density 0.038%

    No Known Activations