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

    Neuronpedia

    INDEX
    Explanations

    opponent cum

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    оло
    1.10
    ग्राहक
    1.09
    nější
    1.06
    later
    1.06
     клиен
    1.02
    alan
    1.00
     cinerea
    0.98
    issements
    0.97
    infile
    0.96
    clients
    0.95
    POSITIVE LOGITS
     honors
    1.10
     Calculator
    0.94
     Calculation
    0.93
     For
    0.93
     Provide
    0.93
     Highest
    0.93
     höchsten
    0.92
     Erkennt
    0.90
    0.90
     faz
    0.89
    Act Density 0.001%

    No Known Activations