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

    Neuronpedia

    INDEX
    Explanations

    addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worm
    -0.08
    ❯
    -0.07
     IPO
    -0.07
     Coupe
    -0.07
    梨
    -0.07
    pone
    -0.07
    ᵐ
    -0.07
     throughput
    -0.07
    市公安局
    -0.06
    狐
    -0.06
    POSITIVE LOGITS
    (ids
    0.07
    (core
    0.07
    (et
    0.07
    .DAY
    0.07
     ellas
    0.07
     Regel
    0.07
     //}↵
    0.07
    的梦想
    0.06
     unequiv
    0.06
    (static
    0.06
    Act Density 0.020%

    No Known Activations