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

    Neuronpedia

    INDEX
    Explanations

    closing eyes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     miscon
    -0.07
     tackle
    -0.07
     misunderstood
    -0.07
     falsch
    -0.07
    ooked
    -0.07
     newer
    -0.07
    追加
    -0.07
     sequel
    -0.07
    ][_
    -0.07
    Principal
    -0.07
    POSITIVE LOGITS
     Brief
    0.09
    Brief
    0.09
     الداخلي
    0.09
     ചടങ്ങ
    0.08
     الدخول
    0.08
     शांत
    0.08
     ყურადღ
    0.08
     zih
    0.08
     തുടങ്ങ
    0.08
     Before
    0.08
    Act Density 0.019%

    No Known Activations