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

    Neuronpedia

    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zeichnet
    -0.07
    (context
    -0.06
    sgiving
    -0.06
     достиг
    -0.06
    p
    -0.06
    |[
    -0.06
    Activity
    -0.06
    řet
    -0.06
    cassert
    -0.06
    hours
    -0.06
    POSITIVE LOGITS
    _approved
    0.08
    WebResponse
    0.07
     trò
    0.07
    غات
    0.07
    243
    0.06
     sink
    0.06
     UNIVERSITY
    0.06
    _DEF
    0.06
    _UN
    0.06
     Law
    0.06
    Act Density 0.006%

    No Known Activations