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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    辩
    -0.08
    oss
    -0.07
     Bali
    -0.07
     Gui
    -0.07
    vel
    -0.07
     Pun
    -0.07
    얀
    -0.07
     Wine
    -0.07
     spice
    -0.07
    break
    -0.06
    POSITIVE LOGITS
    罅
    0.07
    ACHINE
    0.07
     democrat
    0.07
    .pageSize
    0.07
    	TRACE
    0.06
    обеспечен
    0.06
    -operation
    0.06
    劄
    0.06
     unten
    0.06
     Özel
    0.06
    Act Density 0.000%

    No Known Activations