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

    Neuronpedia

    INDEX
    Explanations

    median calculation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    мас
    -0.08
     sequel
    -0.08
    สำนักงานใหญ่
    -0.08
    ijt
    -0.08
    ೋಜ
    -0.08
     eki
    -0.08
     অল
    -0.07
     Fired
    -0.07
     kaiken
    -0.07
     exhibition
    -0.07
    POSITIVE LOGITS
    53
    0.08
     percentile
    0.08
     �
    0.08
     shoulders
    0.07
     vaginal
    0.07
    94
    0.07
     mattresses
    0.07
    ρώ
    0.07
     spoon
    0.07
     confort
    0.07
    Act Density 0.007%

    No Known Activations