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

    Neuronpedia

    INDEX
    Explanations

    safety and sanitation procedures

    np_max-act · gemini-2.0-flash

    terms related to infection prevention and control practices in healthcare settings.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on directive or instructional language—especially imperative verbs used in procedural guidelines.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    wo
    -0.07
     Balt
    -0.07
    Err
    -0.06
    ков
    -0.06
    -divider
    -0.06
    XH
    -0.06
     Vincent
    -0.06
    �
    -0.06
     JDK
    -0.06
    ，要
    -0.06
    POSITIVE LOGITS
     Homo
    0.07
    _EXPR
    0.07
     crian
    0.07
    ACING
    0.06
    //--------------------------------------------------------------↵
    0.06
    acing
    0.06
    OOT
    0.06
    classified
    0.06
     ＜
    0.06
    rasing
    0.06
    Act Density 0.004%

    No Known Activations