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

    Neuronpedia

    INDEX
    Explanations

    something must be seen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blockchain
    -0.08
     }
    -0.08
     eryth
    -0.08
     throughout
    -0.08
     Salem
    -0.08
    (host
    -0.07
    ">
↵
    -0.07
     }}>↵
    -0.07
     HM
    -0.07
    }">↵
    -0.07
    POSITIVE LOGITS
    体验
    0.09
     firsthand
    0.09
     unpleasant
    0.09
     exhilarating
    0.09
     überzeugt
    0.09
    ogat
    0.09
     nasty
    0.08
     exhilar
    0.08
     disgusting
    0.08
     mesmerizing
    0.08
    Act Density 0.132%

    No Known Activations