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

    Neuronpedia

    INDEX
    Explanations

    ader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MADE
    -0.07
     Multip
    -0.06
     encuent
    -0.06
    ンデ
    -0.06
    Dé
    -0.06
     Edwards
    -0.06
    材料
    -0.06
    (element
    -0.06
    ขณะ
    -0.06
    MM
    -0.06
    POSITIVE LOGITS
    	perror
    0.07
    сер
    0.07
    arna
    0.07
     먹
    0.06
    cea
    0.06
    ework
    0.06
     btw
    0.06
    @n
    0.06
    -topic
    0.06
     acclaim
    0.06
    Act Density 0.000%

    No Known Activations