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

    Neuronpedia

    INDEX
    Explanations

    normal

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of experimental group or condition labels (e.g. “normal,” “control,” group identifiers) in scientific study descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     مار
    -0.06
     adept
    -0.06
    And
    -0.06
     invalid
    -0.06
    šem
    -0.06
    _SA
    -0.06
     Wahl
    -0.06
    olog
    -0.06
    وش
    -0.06
    ワー
    -0.05
    POSITIVE LOGITS
    诊
    0.08
    navbarDropdown
    0.07
    actionDate
    0.07
    "Yeah
    0.07
    serie
    0.06
    ekyll
    0.06
    resource
    0.06
     komplex
    0.06
     Schn
    0.06
     Merch
    0.06
    Act Density 0.023%

    No Known Activations