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

    Neuronpedia

    INDEX
    Explanations

    consent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _At
    -0.07
     rub
    -0.07
     dab
    -0.07
     ід
    -0.06
     "@/
    -0.06
    い
    -0.06
    <Value
    -0.06
     Yue
    -0.06
    Gatt
    -0.06
     ern
    -0.06
    POSITIVE LOGITS
    claims
    0.07
    ]
    0.07
     особенно
    0.06
     CLAIM
    0.06
     INTERNAL
    0.06
    SL
    0.06
     mechanisms
    0.06
     overview
    0.06
    】【
    0.06
     ordinance
    0.06
    Act Density 0.001%

    No Known Activations