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

    Neuronpedia

    INDEX
    Explanations

    pre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Government
    -0.07
     misunderstand
    -0.07
     honour
    -0.06
     Britt
    -0.06
    274
    -0.06
    أت
    -0.06
     Vaccine
    -0.06
     playground
    -0.06
     BEST
    -0.06
     symptom
    -0.06
    POSITIVE LOGITS
    ilestone
    0.07
    efault
    0.06
    ่วย
    0.06
     americ
    0.06
     suy
    0.06
    <UFunction
    0.06
    .isSuccess
    0.06
    тиров
    0.06
     doğ
    0.06
    เกษตร
    0.06
    Act Density 0.138%

    No Known Activations