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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ol
    -0.07
     TEST
    -0.07
     Oversight
    -0.07
     Cul
    -0.07
    -delay
    -0.06
     choice
    -0.06
    ‌باشد
    -0.06
     desired
    -0.06
     Yol
    -0.06
    stacles
    -0.06
    POSITIVE LOGITS
    (any
    0.06
     UAV
    0.06
     authenticity
    0.06
    .assertThat
    0.06
     byteArray
    0.06
     gifted
    0.06
     contends
    0.05
     (__
    0.05
    jdk
    0.05
     пат
    0.05
    Act Density 0.006%

    No Known Activations