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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ump
    -0.06
     experimenting
    -0.06
    462
    -0.06
     swapped
    -0.06
    Seat
    -0.06
    Slots
    -0.06
    (CH
    -0.06
    這
    -0.06
     Warm
    -0.06
     dough
    -0.06
    POSITIVE LOGITS
    :int
    0.07
    ]."
    0.07
     lstm
    0.07
     khổ
    0.07
    erved
    0.07
    _mp
    0.07
     Citation
    0.06
     Homepage
    0.06
    /generated
    0.06
    <pcl
    0.06
    Act Density 0.002%

    No Known Activations