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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of institutional ethics or review board approval (e.g., IRB/ethics committee approval statements).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Hub
    -0.07
    SSI
    -0.06
    NOW
    -0.06
    cur
    -0.06
    <section
    -0.06
    ej
    -0.06
     illustrate
    -0.06
    Patrick
    -0.06
     UT
    -0.06
    Mor
    -0.06
    POSITIVE LOGITS
    _j
    0.07
    thora
    0.07
     Shortcut
    0.06
     redesigned
    0.06
    Straight
    0.06
     romant
    0.06
     recipro
    0.06
    GeneratedValue
    0.06
    (cl
    0.06
    рия
    0.06
    Act Density 0.001%

    No Known Activations