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

    Neuronpedia

    INDEX
    Explanations

    pool

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ễn
    -0.08
    too
    -0.07
     Instructor
    -0.07
    igon
    -0.07
    幂
    -0.07
    /count
    -0.07
    实木
    -0.07
    .goods
    -0.07
    IGH
    -0.06
    负载
    -0.06
    POSITIVE LOGITS
     нару
    0.08
    Nine
    0.07
     erroneous
    0.07
     pens
    0.07
    샙
    0.07
    拿到
    0.06
     assembling
    0.06
     atrocities
    0.06
    中枢
    0.06
    icha
    0.06
    Act Density 0.017%

    No Known Activations