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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and connector words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hemp
    -0.07
    潇
    -0.07
     Dad
    -0.06
    贝壳
    -0.06
    iPad
    -0.06
    屺
    -0.06
    怼
    -0.06
    不然
    -0.06
    ้าน
    -0.06
    -play
    -0.06
    POSITIVE LOGITS
     успешно
    0.07
    undi
    0.07
     rects
    0.06
    Sa
    0.06
    ﮁ
    0.06
    PF
    0.06
     Ch
    0.06
    	User
    0.06
    /ch
    0.06
     Processes
    0.06
    Act Density 0.278%

    No Known Activations