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

    Neuronpedia

    INDEX
    Explanations

    water droplets in clouds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    荏
    0.50
    凵
    0.49
    Hotkey
    0.45
    郸
    0.44
    螈
    0.43
     विश्वसनीयता
    0.43
    瘘
    0.43
     তন্ত্র
    0.42
    SubDirectory
    0.42
    蒯
    0.41
    POSITIVE LOGITS
     cloud
    1.60
     clouds
    1.56
     aerosols
    1.48
     aerosol
    1.36
    雲
    1.33
     Cloud
    1.30
     Clouds
    1.30
    cloud
    1.27
    Cloud
    1.23
    clouds
    1.23
    Act Density 0.035%

    No Known Activations