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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /il
    -0.08
     Tou
    -0.07
     trä
    -0.07
     hac
    -0.07
     �
    -0.07
     ila
    -0.07
     bland
    -0.07
    Vy
    -0.07
     bruises
    -0.07
    的带领
    -0.07
    POSITIVE LOGITS
     ModelState
    0.08
    בקש
    0.07
     Dallas
    0.07
    (',');↵
    0.07
    itive
    0.07
    צפוי
    0.07
     suspend
    0.07
     }()↵
    0.07
    很大程度
    0.07
    IENTATION
    0.07
    Act Density 0.000%

    No Known Activations