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

    Neuronpedia

    INDEX
    Explanations

    boolean logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     사람
    -0.07
    IMATION
    -0.06
    yield
    -0.06
    Songs
    -0.06
    	world
    -0.06
    prob
    -0.06
    .componentInstance
    -0.06
    ortex
    -0.06
     Tin
    -0.06
    ernels
    -0.06
    POSITIVE LOGITS
     recognized
    0.08
     imperial
    0.07
     Melania
    0.06
    ійного
    0.06
     […]↵↵
    0.06
     canine
    0.06
     ویژه
    0.06
    Solo
    0.06
                ↵↵
    0.06
     숙
    0.06
    Act Density 0.042%

    No Known Activations