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
    continent
    -0.07
    BuildContext
    -0.06
     wal
    -0.06
     Hardcover
    -0.06
    ंख
    -0.06
     circumcision
    -0.06
     slows
    -0.06
     καθ
    -0.06
     franchise
    -0.06
    stress
    -0.06
    POSITIVE LOGITS
    ?('
    0.07
    nelly
    0.07
    refund
    0.07
    _DEVICE
    0.07
    /basic
    0.07
    _Stream
    0.06
    ErrorException
    0.06
    ENCED
    0.06
    (y
    0.06
    lang
    0.06
    Act Density 0.000%

    No Known Activations