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

    Neuronpedia

    INDEX
    Explanations

    Monday

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     eruption
    -0.08
    ythe
    -0.07
     яке
    -0.07
    これ
    -0.07
    imitive
    -0.07
     caves
    -0.07
     Butterfly
    -0.07
    236
    -0.07
     Ru
    -0.07
    ortality
    -0.06
    POSITIVE LOGITS
     Monday
    0.13
    Monday
    0.12
    manship
    0.07
     monday
    0.07
    ($('#
    0.07
    -load
    0.06
     Moses
    0.06
    marked
    0.06
    (mac
    0.06
     Mickey
    0.06
    Act Density 0.005%

    No Known Activations