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

    Neuronpedia

    INDEX
    Explanations

    RedPajama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Since
    0.42
    Scenario
    0.39
    Sales
    0.38
    Don
    0.38
    او
    0.38
    快乐
    0.38
    Mileage
    0.37
    ☺
    0.37
    Как
    0.36
    stats
    0.36
    POSITIVE LOGITS
     Jew
    0.62
     Echo
    0.57
     pawn
    0.49
     ജൂ
    0.48
     Juda
    0.48
     Juno
    0.48
     tah
    0.47
     ICO
    0.47
     Brahman
    0.46
     echo
    0.45
    Act Density 0.001%

    No Known Activations