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

    Neuronpedia

    INDEX
    Explanations

    warm temperatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    1.70
    ro
    1.47
    ה
    1.45
     longe
    1.43
    ます
    1.41
    AVA
    1.41
    И
    1.41
    ুল
    1.40
     gour
    1.40
    𝐏
    1.39
    POSITIVE LOGITS
     temperatures
    1.91
     Temperatures
    1.79
     Temperaturen
    1.72
     температура
    1.68
    0
    1.52
     overheating
    1.50
     온도
    1.48
     temperaturas
    1.38
     warms
    1.38
     temperature
    1.38
    Act Density 0.265%

    No Known Activations