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

    Neuronpedia

    INDEX
    Explanations

    merits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confusing
    -0.07
    病院
    -0.07
    gae
    -0.06
    ovny
    -0.06
    /admin
    -0.06
     thơm
    -0.06
    slash
    -0.06
    bane
    -0.06
    ascript
    -0.06
    混
    -0.06
    POSITIVE LOGITS
     sandwiches
    0.07
     contrib
    0.06
    を
    0.06
    本当
    0.06
    Missing
    0.06
    Interest
    0.06
     ration
    0.06
     redeem
    0.06
     separating
    0.06
    implements
    0.06
    Act Density 0.002%

    No Known Activations