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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ===
    -0.06
     Smartphone
    -0.06
    >We
    -0.06
    	types
    -0.06
    ніх
    -0.06
     груп
    -0.06
    供应
    -0.06
    кс
    -0.06
    price
    -0.06
     stresses
    -0.06
    POSITIVE LOGITS
    (ofSize
    0.09
     perception
    0.07
     saline
    0.07
    _led
    0.06
    eneration
    0.06
     Util
    0.06
     masked
    0.06
     sdl
    0.06
    floor
    0.06
     negotiated
    0.06
    Act Density 0.097%

    No Known Activations