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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    讀
    -0.07
    实验
    -0.07
     막
    -0.07
    #elif
    -0.07
    一度
    -0.06
     Ад
    -0.06
     benim
    -0.06
    	connection
    -0.06
    .AddComponent
    -0.06
    TEMPL
    -0.06
    POSITIVE LOGITS
    orgia
    0.07
    กลาง
    0.06
     pores
    0.06
     Bones
    0.06
     vog
    0.06
     working
    0.06
    ropsych
    0.06
    romatic
    0.06
    rish
    0.06
     --↵
    0.06
    Act Density 0.058%

    No Known Activations