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

    Neuronpedia

    INDEX
    Explanations

    temperature and weather conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flown
    0.77
     facelift
    0.74
     questioned
    0.72
     accrued
    0.72
     reworked
    0.72
     Penta
    0.72
     performed
    0.71
     fraught
    0.71
     understated
    0.71
     network
    0.70
    POSITIVE LOGITS
     температура
    1.79
     temperatures
    1.77
     Temperatures
    1.73
     Temperaturen
    1.67
    Temperatura
    1.66
     temperatura
    1.64
     température
    1.63
     températures
    1.61
     Temperature
    1.59
    Temperature
    1.59
    Act Density 0.901%

    No Known Activations