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

    Neuronpedia

    INDEX
    Explanations

    ul

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on the letter sequence “ul” (as in valvuloplasty, folliculogenesis, ventriculography, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (zone
    -0.07
    patients
    -0.06
     polít
    -0.06
    Mozilla
    -0.06
    ์เน
    -0.06
    自然
    -0.06
    立刻
    -0.06
    вают
    -0.06
    eme
    -0.06
     çok
    -0.06
    POSITIVE LOGITS
     prag
    0.07
    _expand
    0.06
    ghan
    0.06
     �
    0.06
    -function
    0.06
     violating
    0.06
     комплекс
    0.06
    abil
    0.06
     modifying
    0.06
    Rpc
    0.06
    Act Density 0.249%

    No Known Activations