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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SEL
    -0.07
    OH
    -0.07
     DateTimeKind
    -0.07
    <th
    -0.06
    ...)↵
    -0.06
    коп
    -0.06
    enabled
    -0.06
     quaternion
    -0.06
    uce
    -0.06
    уж
    -0.06
    POSITIVE LOGITS
    Completed
    0.06
     anlaş
    0.06
     několika
    0.06
     cabinets
    0.06
     enquiry
    0.06
     ένα
    0.06
     innocent
    0.06
    股票
    0.06
     розташ
    0.06
     choosing
    0.06
    Act Density 0.006%

    No Known Activations