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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spoon
    -0.07
    阄
    -0.06
    HttpContext
    -0.06
    ｃ
    -0.06
    committed
    -0.06
     accompl
    -0.06
    assertEquals
    -0.06
    ONY
    -0.06
    恶劣
    -0.06
    ทดสอบ
    -0.06
    POSITIVE LOGITS
    .lu
    0.07
    心理学
    0.07
    .LocalDate
    0.07
     biased
    0.07
     число
    0.07
     humanitarian
    0.07
    ächst
    0.07
    bial
    0.06
     laws
    0.06
    .error
    0.06
    Act Density 0.027%

    No Known Activations