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

    Neuronpedia

    INDEX
    Explanations

    accumulators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Route
    -0.08
    ออกแบบ
    -0.08
    ugh
    -0.08
     Burst
    -0.07
    适时
    -0.07
    昴
    -0.07
    تمتع
    -0.07
    风景区
    -0.07
    裨
    -0.07
    素质
    -0.07
    POSITIVE LOGITS
     יודעים
    0.07
    ^(
    0.07
     pragma
    0.06
    른
    0.06
     trois
    0.06
    囹
    0.06
     Cage
    0.06
     closed
    0.06
    ):(
    0.06
     אחרת
    0.06
    Act Density 0.002%

    No Known Activations