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

    Neuronpedia

    INDEX
    Explanations

    x-ray

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ALS
    -0.07
     Stores
    -0.06
    dock
    -0.06
     Montgomery
    -0.06
     Prop
    -0.06
     mkdir
    -0.06
     Calder
    -0.06
     pró
    -0.06
     filtro
    -0.06
     ル
    -0.06
    POSITIVE LOGITS
     ξ
    0.07
     booty
    0.06
     alphabetical
    0.06
    ुरक
    0.06
     hos
    0.06
    درس
    0.06
    orelease
    0.06
     Levi
    0.06
    TRGL
    0.06
    文学
    0.06
    Act Density 0.006%

    No Known Activations