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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of formal research or funding institutions (e.g. “National Institute of Health,” “National Institute of Mental Health,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     стат
    -0.07
     теч
    -0.06
     Doing
    -0.06
    	user
    -0.06
     lastIndex
    -0.06
    _AM
    -0.06
    PHA
    -0.05
    /cart
    -0.05
    Wednesday
    -0.05
    EFI
    -0.05
    POSITIVE LOGITS
    Michigan
    0.07
     osg
    0.07
     surprise
    0.07
    Contents
    0.06
     recuper
    0.06
    .contentMode
    0.06
    ght
    0.06
    속
    0.06
     permissions
    0.06
     scholarships
    0.06
    Act Density 0.006%

    No Known Activations