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

    Neuronpedia

    INDEX
    Explanations

    country representation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	loc
    -0.07
    िथ
    -0.07
     knots
    -0.07
    陰
    -0.07
    ),$
    -0.06
     либо
    -0.06
     Initializing
    -0.06
    ….
    -0.06
     či
    -0.06
     ως
    -0.06
    POSITIVE LOGITS
     necesita
    0.07
    ATAR
    0.07
     langue
    0.06
     Log
    0.06
     pricing
    0.06
     Dave
    0.06
     Freddy
    0.06
     Doom
    0.06
     poems
    0.06
    Super
    0.06
    Act Density 0.009%

    No Known Activations