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

    Neuronpedia

    INDEX
    Explanations

    Graham

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Elsa
    -0.06
     Pins
    -0.06
     Nail
    -0.06
     dign
    -0.06
     Reynolds
    -0.06
     Rück
    -0.06
     Tire
    -0.06
     مربوط
    -0.06
     PHYS
    -0.06
     二
    -0.06
    POSITIVE LOGITS
     Graham
    0.09
    raham
    0.08
    597
    0.08
    Overall
    0.07
    ار
    0.07
     kk
    0.07
     bağlantı
    0.07
     warped
    0.06
     strugg
    0.06
    ARED
    0.06
    Act Density 0.019%

    No Known Activations