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

    Neuronpedia

    INDEX
    Explanations

    art

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
     Between
    -0.07
    -0.06
    licts
    -0.06
    標準
    -0.06
    _profit
    -0.06
    -0.06
     staples
    -0.06
     easiest
    -0.06
    both
    -0.06
    POSITIVE LOGITS
     PUS
    0.07
     TRAN
    0.07
    -ajax
    0.06
     pollut
    0.06
     visitor
    0.06
     laboratory
    0.06
     kang
    0.06
    Pakistan
    0.06
     hdf
    0.06
    Ace
    0.06
    Act Density 0.001%

    No Known Activations