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

    Neuronpedia

    INDEX
    Explanations

    except

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finan
    -0.07
     Nolan
    -0.07
    mia
    -0.07
    bu
    -0.07
     Tian
    -0.07
    Binary
    -0.07
    Bio
    -0.07
     Huffman
    -0.07
     Naw
    -0.07
    Amy
    -0.07
    POSITIVE LOGITS
     except
    0.11
     Except
    0.11
    Except
    0.10
    except
    0.08
    	except
    0.08
     interiors
    0.07
     Last
    0.07
     EX
    0.07
    pt
    0.07
     caps
    0.07
    Act Density 0.007%

    No Known Activations