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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     своїх
    -0.09
    ierte
    -0.07
     insanların
    -0.06
    .seed
    -0.06
    vehicle
    -0.06
     Rockets
    -0.06
     Що
    -0.06
    chs
    -0.06
    -_
    -0.06
    覚
    -0.06
    POSITIVE LOGITS
     embodiment
    0.07
    .GREEN
    0.06
     Round
    0.06
    inner
    0.06
    "A
    0.06
    ridge
    0.06
    ATCH
    0.06
    희
    0.06
     Circle
    0.06
    (sem
    0.06
    Act Density 0.074%

    No Known Activations