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

    Neuronpedia

    INDEX
    Explanations

    PT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jas
    -0.07
     rico
    -0.06
     descendant
    -0.06
     sư
    -0.06
    mons
    -0.06
    oca
    -0.06
     hs
    -0.06
    datum
    -0.06
    \a
    -0.06
     respected
    -0.06
    POSITIVE LOGITS
    ال
    0.07
     kiss
    0.07
     OG
    0.07
    Parcelable
    0.07
    AGAIN
    0.06
    -top
    0.06
     нож
    0.06
     Batter
    0.06
    اي
    0.06
     hookup
    0.06
    Act Density 0.000%

    No Known Activations