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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     şeh
    -0.07
     MAT
    -0.06
    ith
    -0.06
     hå
    -0.06
     так
    -0.06
     \<
    -0.06
     tướng
    -0.06
     올
    -0.06
    	sc
    -0.06
     만나
    -0.06
    POSITIVE LOGITS
     doğr
    0.07
    .inspect
    0.06
    葡
    0.06
     qualifiers
    0.06
    Ν
    0.06
    iyel
    0.06
     Encode
    0.06
     Dairy
    0.06
     plumber
    0.06
     Mond
    0.06
    Act Density 0.002%

    No Known Activations