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

    Neuronpedia

    INDEX
    Explanations

    code algorithms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     luder
    -0.07
     xPos
    -0.06
     dny
    -0.06
    六
    -0.06
     Como
    -0.06
     Conse
    -0.06
     Express
    -0.06
     Protected
    -0.06
    érc
    -0.06
     hours
    -0.06
    POSITIVE LOGITS
    />.↵↵
    0.08
    }"↵
    0.07
     позвол
    0.07
     subscribe
    0.06
     }]↵
    0.06
    ;.
    0.06
     FN
    0.06
     대한민국
    0.06
    ')])↵
    0.06
    <ArrayList
    0.06
    Act Density 0.003%

    No Known Activations