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

    Neuronpedia

    INDEX
    Explanations

    groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ladd
    -0.08
    手续
    -0.08
     ata
    -0.08
     рестора
    -0.08
    rack
    -0.08
     Chennai
    -0.08
     собственного
    -0.08
    abre
    -0.08
    Zoo
    -0.07
     maria
    -0.07
    POSITIVE LOGITS
    群
    0.12
     populations
    0.11
     населения
    0.10
     subset
    0.10
     cohorts
    0.09
    gruppe
    0.09
    subset
    0.09
     subsets
    0.09
     population
    0.09
     workforce
    0.09
    Act Density 0.036%

    No Known Activations