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

    Neuronpedia

    INDEX
    Explanations

    coordinate space transformations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TR
    -0.07
    aghan
    -0.07
     tourist
    -0.07
     Tibetan
    -0.06
     Speaker
    -0.06
     piracy
    -0.06
    _media
    -0.06
    Minnesota
    -0.06
    INCLUDED
    -0.06
    stad
    -0.06
    POSITIVE LOGITS
     �
    0.07
    aceous
    0.07
     виб
    0.06
    �
    0.06
     효
    0.06
     後
    0.06
    宋
    0.06
     edilm
    0.06
     zoek
    0.06
     casa
    0.06
    Act Density 0.012%

    No Known Activations