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

    Neuronpedia

    INDEX
    Explanations

    Maximization problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (nt
    -0.08
     conservation
    -0.07
     достаточно
    -0.07
    Law
    -0.07
    (/\
    -0.07
    nt
    -0.07
     nt
    -0.07
    _should
    -0.07
     cartoons
    -0.07
    _duplicates
    -0.07
    POSITIVE LOGITS
    ,max
    0.10
     استف
    0.09
     conceivable
    0.09
     imaginable
    0.08
     allowable
    0.08
     attainable
    0.08
     maksimal
    0.08
     obtainable
    0.08
     ممكن
    0.08
    ,min
    0.08
    Act Density 0.071%

    No Known Activations