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

    Neuronpedia

    INDEX
    Explanations

    Array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (connect
    -0.07
    主任
    -0.07
    -title
    -0.07
     impression
    -0.07
     frequent
    -0.06
     COMPLETE
    -0.06
     Dane
    -0.06
     descargar
    -0.06
    같
    -0.06
     resolutions
    -0.06
    POSITIVE LOGITS
    Trigger
    0.07
    ABCDEFGHI
    0.06
    _SZ
    0.06
    Hz
    0.06
     vyd
    0.06
     "**
    0.06
    итом
    0.06
     cí
    0.06
     steer
    0.06
    ">$
    0.06
    Act Density 0.003%

    No Known Activations