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

    Neuronpedia

    INDEX
    Explanations

    можно

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    哺乳
    -0.08
    肱
    -0.07
    .est
    -0.07
    Network
    -0.07
     autoplay
    -0.07
     vö
    -0.07
    zellik
    -0.07
    isNew
    -0.07
     wcześ
    -0.07
    𐍂
    -0.07
    POSITIVE LOGITS
     можно
    0.09
     justices
    0.07
    对策
    0.07
     нельзя
    0.07
    学者
    0.07
     nghị
    0.07
     Well
    0.07
     bait
    0.07
     следует
    0.07
     Можно
    0.07
    Act Density 0.017%

    No Known Activations