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
    -inline
    -0.07
    維
    -0.07
    arya
    -0.07
     randomized
    -0.07
    Ｙ
    -0.07
     서비스
    -0.06
     Fallen
    -0.06
    scope
    -0.06
    nees
    -0.06
     movers
    -0.06
    POSITIVE LOGITS
     анг
    0.06
    рг
    0.06
     Госп
    0.06
    ........
    0.06
    Prom
    0.06
     vamos
    0.06
    약
    0.06
     συμπ
    0.06
     trú
    0.06
    ................
    0.06
    Act Density 0.041%

    No Known Activations