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

    Neuronpedia

    INDEX
    Explanations

    oping

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spirit
    -0.09
    .transport
    -0.09
     spirit
    -0.08
    Spirit
    -0.07
    ері
    -0.07
     tinh
    -0.07
     sile
    -0.07
    pap
    -0.07
    ล
    -0.07
     Hamilton
    -0.07
    POSITIVE LOGITS
     находится
    0.08
     warms
    0.08
     foreigners
    0.08
    不停
    0.08
    �
    0.07
    _confirmation
    0.07
     �
    0.07
     wichtigsten
    0.07
     गर
    0.07
     outdoors
    0.07
    Act Density 0.002%

    No Known Activations