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

    Neuronpedia

    INDEX
    Explanations

    severity

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of “severity” (and its variations) in clinical or medical contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Active
    -0.07
    _OPEN
    -0.07
    getSingleton
    -0.07
     services
    -0.06
     mails
    -0.06
    ơm
    -0.06
    _PRINT
    -0.06
    従
    -0.06
     müz
    -0.06
    some
    -0.06
    POSITIVE LOGITS
     severity
    0.08
     rou
    0.06
    )V
    0.06
     Parr
    0.06
    _pal
    0.06
    bell
    0.06
     симптомы
    0.06
    .Amount
    0.06
     Reactive
    0.06
    ฤ
    0.06
    Act Density 0.014%

    No Known Activations