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

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heartbeat
    -0.07
     Deal
    -0.07
     comprehension
    -0.07
     costs
    -0.07
     atoms
    -0.06
     management
    -0.06
     Kế
    -0.06
     Manage
    -0.06
    .AbsoluteConstraints
    -0.06
    алу
    -0.06
    POSITIVE LOGITS
    那个
    0.07
     Picasso
    0.07
     tamil
    0.06
    subplot
    0.06
     Hindi
    0.06
     Schwar
    0.06
     Burk
    0.06
     противоп
    0.06
     fir
    0.06
    ="__
    0.06
    Act Density 0.018%

    No Known Activations