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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _POINTER
    -0.07
    -striped
    -0.06
     trajectory
    -0.06
    经验
    -0.06
     Dragon
    -0.06
     Parcel
    -0.06
    ція
    -0.06
     Oktober
    -0.06
    Mapping
    -0.06
     계약
    -0.06
    POSITIVE LOGITS
    .use
    0.07
    ्‍
    0.07
    udas
    0.07
    �
    0.07
     ['#
    0.06
     getRandom
    0.06
    博
    0.06
    fac
    0.06
    洁
    0.06
     devuelve
    0.06
    Act Density 0.104%

    No Known Activations