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

    Neuronpedia

    INDEX
    Explanations

    community

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ペ
    -0.07
    宽
    -0.06
     hn
    -0.06
     Passenger
    -0.06
     گوش
    -0.06
    .analysis
    -0.06
     chỗ
    -0.06
     разд
    -0.06
     trouble
    -0.06
     дуже
    -0.06
    POSITIVE LOGITS
     society
    0.07
     italiano
    0.07
    _ELEMENT
    0.07
    截
    0.07
     Symposium
    0.06
    oggler
    0.06
    _LIGHT
    0.06
     trval
    0.06
     Community
    0.06
     Amsterdam
    0.06
    Act Density 0.015%

    No Known Activations