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

    Neuronpedia

    INDEX
    Explanations

    limit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     observers
    -0.07
     ער
    -0.07
     makeover
    -0.07
     mũi
    -0.07
     фут
    -0.07
    john
    -0.06
    เต
    -0.06
     tally
    -0.06
     Football
    -0.06
    太平
    -0.06
    POSITIVE LOGITS
    индив
    0.08
    🗓
    0.07
    ��
    0.07
    �
    0.07
     bại
    0.07
     kad
    0.07
    ◦
    0.07
    单车
    0.07
    :NSLocalizedString
    0.07
    (sk
    0.07
    Act Density 0.004%

    No Known Activations