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

    Neuronpedia

    INDEX
    Explanations

    guid

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of image‐guided procedures (e.g. “CT-guided,” “ultrasound-guided,” or general “guidance”) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (HTTP
    -0.07
    _ax
    -0.06
     человечес
    -0.06
    .read
    -0.06
    /down
    -0.06
    (categories
    -0.06
     الجم
    -0.06
     vistas
    -0.06
     rend
    -0.06
     Teil
    -0.06
    POSITIVE LOGITS
     inventor
    0.07
     *\
    0.07
     disemb
    0.07
    恵
    0.06
    >:
    0.06
     dissert
    0.06
    dbg
    0.06
     textStatus
    0.06
    ?',↵
    0.06
    ],[
    0.06
    Act Density 0.003%

    No Known Activations