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

    Neuronpedia

    INDEX
    Explanations

    knight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fences
    -0.07
     agosto
    -0.07
    .Lo
    -0.07
     Eastern
    -0.07
    .lo
    -0.07
     Rp
    -0.06
     DSP
    -0.06
     độ
    -0.06
    	system
    -0.06
     dc
    -0.06
    POSITIVE LOGITS
     Knight
    0.22
     knight
    0.17
    Knight
    0.17
     Knights
    0.14
     knights
    0.11
    ights
    0.09
    IGHT
    0.08
     Nightmare
    0.08
    night
    0.08
     Cavaliers
    0.07
    Act Density 0.003%

    No Known Activations