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

    Neuronpedia

    INDEX
    Explanations

    urination

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on tokens referring to bladder‐emptying actions or urinary voiding terms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     crossings
    -0.07
    _LAYOUT
    -0.06
    zel
    -0.06
     hips
    -0.06
     ampl
    -0.06
    보험
    -0.06
    арів
    -0.06
    lası
    -0.06
     TSA
    -0.06
     Kale
    -0.06
    POSITIVE LOGITS
     şart
    0.07
    andex
    0.06
     isNaN
    0.06
    (class
    0.06
     sever
    0.06
     adorned
    0.06
    кої
    0.06
     ford
    0.06
    ITICAL
    0.06
    ife
    0.06
    Act Density 0.004%

    No Known Activations