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

    Neuronpedia

    INDEX
    Explanations

    Bearings, parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hyde
    -0.08
     affich
    -0.08
     bonus
    -0.08
    ieux
    -0.08
    語
    -0.08
     disclosure
    -0.08
     ajout
    -0.08
     synthes
    -0.08
     fiction
    -0.08
     offense
    -0.08
    POSITIVE LOGITS
     Bearings
    0.10
     bearings
    0.09
    Bearing
    0.09
     flange
    0.09
    SAN
    0.08
     cushioning
    0.08
    чик
    0.08
    sker
    0.08
    (theta
    0.08
     fre
    0.08
    Act Density 0.004%

    No Known Activations