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

    Neuronpedia

    INDEX
    Explanations

    UFO conspiracies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Detection
    -0.08
    _detection
    -0.08
     ఇప్పటికే
    -0.08
     detects
    -0.08
    “四
    -0.08
    已经
    -0.08
     Bes
    -0.07
    半年
    -0.07
    检测
    -0.07
     Detection
    -0.07
    POSITIVE LOGITS
     neki
    0.09
     دسته
    0.08
     dents
    0.08
     neke
    0.08
    /category
    0.08
     hardworking
    0.08
     klima
    0.07
     wishlist
    0.07
     #'
    0.07
    iwe
    0.07
    Act Density 0.003%

    No Known Activations