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
     sớm
    -0.07
    大理
    -0.07
    tó
    -0.07
    -scal
    -0.07
     Begins
    -0.07
    感冒
    -0.06
    海尔
    -0.06
     deterioration
    -0.06
     Shay
    -0.06
     Bak
    -0.06
    POSITIVE LOGITS
    册
    0.07
    ᕼ
    0.07
    	register
    0.07
     shells
    0.07
     iterable
    0.06
     removed
    0.06
    各行各
    0.06
     Usa
    0.06
     tricks
    0.06
     ticking
    0.06
    Act Density 0.019%

    No Known Activations