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

    Neuronpedia

    INDEX
    Explanations

    warmth and comfort

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     watering
    0.88
     Cucumber
    0.80
     irrigation
    0.79
     irrig
    0.74
     mowing
    0.74
     plak
    0.73
     йил
    0.72
     रैम
    0.72
     sprink
    0.71
     Gymn
    0.71
    POSITIVE LOGITS
     warmth
    1.92
     warms
    1.67
    🧣
    1.61
     Warming
    1.58
     warming
    1.58
     warmed
    1.57
    暖
    1.56
     warmest
    1.54
    Warm
    1.52
     উষ্ণ
    1.52
    Act Density 0.305%

    No Known Activations