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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     logs
    -0.07
     Agreement
    -0.07
    ,List
    -0.07
    .dead
    -0.07
     task
    -0.06
    /task
    -0.06
     objet
    -0.06
    _secure
    -0.06
    hk
    -0.06
    ashboard
    -0.06
    POSITIVE LOGITS
     omin
    0.06
    Dallas
    0.06
     відповід
    0.06
     отримання
    0.06
    apı
    0.06
    UIApplicationDelegate
    0.06
     através
    0.05
     UIApplication
    0.05
     máte
    0.05
    (optarg
    0.05
    Act Density 0.356%

    No Known Activations