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

    Neuronpedia

    INDEX
    Explanations

    ly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bg
    -0.08
     elas
    -0.08
    =array
    -0.08
    Bart
    -0.08
     Bakers
    -0.08
     erl
    -0.08
    nek
    -0.08
    mdl
    -0.07
     turmoil
    -0.07
    loch
    -0.07
    POSITIVE LOGITS
     рекоменду
    0.09
     outweigh
    0.09
     recommend
    0.09
    认为
    0.09
     рекомендуется
    0.08
     encouraged
    0.08
     urge
    0.08
     believe
    0.08
     urged
    0.08
     recomand
    0.08
    Act Density 0.019%

    No Known Activations