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

    Neuronpedia

    INDEX
    Explanations

    environmental conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bungalows
    0.52
     housewife
    0.49
     risotto
    0.46
     গ্রামা
    0.45
     সংসার
    0.43
     housewives
    0.43
     peuple
    0.42
    ्रांत
    0.41
     maisons
    0.41
     bungalow
    0.40
    POSITIVE LOGITS
     temperature
    1.58
    温度
    1.46
    temperature
    1.40
    Temperature
    1.37
     Temperature
    1.34
    溫度
    1.33
     humidity
    1.30
     온도
    1.28
     temperatur
    1.25
     temperatura
    1.24
    Act Density 0.060%

    No Known Activations