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

    Neuronpedia

    INDEX
    Explanations

    important

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _acc
    -0.06
     Через
    -0.06
     refill
    -0.06
    .Help
    -0.06
    ugar
    -0.06
    มา
    -0.06
     عب
    -0.06
     Ninh
    -0.06
    머
    -0.06
     Dispatcher
    -0.06
    POSITIVE LOGITS
    vir
    0.07
     glitter
    0.07
     계약
    0.07
    029
    0.06
     injury
    0.06
    ematic
    0.06
     Ngb
    0.06
     zIndex
    0.06
     elegance
    0.06
     dut
    0.06
    Act Density 0.078%

    No Known Activations