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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shocking
    -0.08
     ActivatedRoute
    -0.07
    UILTIN
    -0.07
     '|
    -0.07
    	TEST
    -0.07
    Br
    -0.06
     Necessary
    -0.06
    reso
    -0.06
     LAW
    -0.06
    итив
    -0.06
    POSITIVE LOGITS
    Ping
    0.06
     člen
    0.06
    اساس
    0.06
    -national
    0.06
     СССР
    0.06
     celkem
    0.06
    	j
    0.06
    -cn
    0.06
    eil
    0.06
    ậm
    0.06
    Act Density 0.037%

    No Known Activations