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

    Neuronpedia

    INDEX
    Explanations

    medical treatment

    np_max-act · gemini-2.0-flash

    This neuron detects document section–heading terms (like “Diagnosis,” “Treatment,” “Symptoms,” “Design,” “Service history,” etc.) that mark structural sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    蓝
    -0.07
    _advanced
    -0.06
    ük
    -0.06
     ARCH
    -0.06
    терес
    -0.06
     latest
    -0.06
    arch
    -0.06
    _BAR
    -0.06
    _root
    -0.06
    _PARENT
    -0.06
    POSITIVE LOGITS
     heightened
    0.07
    cela
    0.07
     "))↵
    0.07
    !=↵
    0.07
    ódigo
    0.07
    .CommandType
    0.07
     destroy
    0.07
     heures
    0.07
    intValue
    0.06
     зак
    0.06
    Act Density 0.194%

    No Known Activations