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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     respect
    -0.07
    .trip
    -0.06
     incoming
    -0.06
     замен
    -0.06
    Network
    -0.06
    -env
    -0.06
    AlmostEqual
    -0.06
     Logistic
    -0.06
    mpi
    -0.06
    ٬
    -0.06
    POSITIVE LOGITS
     closeModal
    0.08
     concaten
    0.07
     stu
    0.06
     powder
    0.06
    τέ
    0.06
     filtro
    0.06
     Someone
    0.06
     fgets
    0.06
     мус
    0.06
     jistě
    0.06
    Act Density 0.002%

    No Known Activations