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

    Neuronpedia

    INDEX
    Explanations

    image

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Node
    -0.07
     Thái
    -0.07
     был
    -0.06
     parity
    -0.06
    enuity
    -0.06
     Talking
    -0.06
     zoekt
    -0.06
    .sex
    -0.06
     forty
    -0.06
     Beginner
    -0.06
    POSITIVE LOGITS
    kening
    0.06
    DataBase
    0.06
     god
    0.06
    μων
    0.06
    رد
    0.06
     luggage
    0.06
    �인
    0.06
    �ng
    0.05
     flights
    0.05
    _MEDIUM
    0.05
    Act Density 0.029%

    No Known Activations