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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fra
    -0.08
    attività
    -0.07
    𝐹
    -0.07
    f
    -0.07
    ノ
    -0.07
    FP
    -0.07
    ,C
    -0.07
    ɦ
    -0.07
    Ot
    -0.06
    ɣ
    -0.06
    POSITIVE LOGITS
    �s
    0.07
     문제
    0.07
    捡
    0.07
    校园
    0.07
     unilateral
    0.06
     opin
    0.06
     много
    0.06
    临港
    0.06
    もら
    0.06
    糯
    0.06
    Act Density 0.073%

    No Known Activations