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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Naming
    -0.08
    endir
    -0.07
    459
    -0.07
     transitional
    -0.07
     Kant
    -0.07
     key
    -0.07
     Fior
    -0.07
     Center
    -0.07
    ancy
    -0.07
     pylab
    -0.07
    POSITIVE LOGITS
    ...
    0.08
    ...'
    0.07
    ..."
    0.07
    ......
    0.07
     BW
    0.07
    ...
    0.07
    ........................
    0.07
    ...↵
    0.07
    ...\
    0.07
    well
    0.07
    Act Density 0.065%

    No Known Activations