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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meinem
    -0.08
    枳
    -0.07
    肚
    -0.07
     Ku
    -0.07
    ibern
    -0.06
    anuts
    -0.06
    窕
    -0.06
    常态
    -0.06
     Thumbnail
    -0.06
     Faster
    -0.06
    POSITIVE LOGITS
    מאה
    0.07
    trajectory
    0.07
    aley
    0.07
     subjected
    0.07
    legend
    0.07
     centers
    0.07
     vibrations
    0.07
     때문이다
    0.07
    divide
    0.07
     sergeant
    0.07
    Act Density 0.001%

    No Known Activations