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

    Neuronpedia

    INDEX
    Explanations

    text continuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maiores
    0.94
     Savo
    0.80
     Sur
    0.80
     Søren
    0.77
     Simulations
    0.77
     Sicher
    0.76
    mountain
    0.75
     Larger
    0.75
    Sue
    0.75
     vanish
    0.74
    POSITIVE LOGITS
     upheld
    0.84
     helpful
    0.74
    ীন
    0.68
    ப்படுகிறது
    0.68
     n
    0.67
     capable
    0.65
     unhealthy
    0.64
     unbeatable
    0.64
    Ho
    0.64
    hoz
    0.64
    Act Density 0.000%

    No Known Activations