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

    Neuronpedia

    INDEX
    Explanations

    rate limiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cowardly
    0.58
     lengthy
    0.54
    nina
    0.54
     reallocation
    0.53
     postdoc
    0.53
     vizsgál
    0.52
     investigar
    0.51
     Covid
    0.50
     potentially
    0.50
     Silva
    0.49
    POSITIVE LOGITS
    Rate
    1.15
     Rate
    1.13
     rate
    1.13
     rates
    1.04
     Rates
    1.00
    Rates
    1.00
     RATE
    0.98
    率
    0.92
    rate
    0.90
    RATE
    0.90
    Act Density 0.009%

    No Known Activations