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

    Neuronpedia

    INDEX
    Explanations

    cooking instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	counter
    -0.07
     cis
    -0.07
    .addHandler
    -0.07
    违背
    -0.07
    tte
    -0.07
    Earn
    -0.07
     Assert
    -0.07
    踊跃
    -0.07
     Zimbabwe
    -0.06
     hundreds
    -0.06
    POSITIVE LOGITS
     presentations
    0.07
    (project
    0.07
    �
    0.07
    ㄒ
    0.07
    計畫
    0.06
    	sub
    0.06
    젼
    0.06
    죙
    0.06
    畢
    0.06
     beberapa
    0.06
    Act Density 0.009%

    No Known Activations