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

    Neuronpedia

    INDEX
    Explanations

    Water Flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mission
    0.69
     qur
    0.68
     Mad
    0.65
     mission
    0.62
     Gyr
    0.61
     Inc
    0.60
     Lith
    0.60
     lim
    0.60
     கட்டு
    0.59
     Ga
    0.58
    POSITIVE LOGITS
    Notifications
    0.61
    notifications
    0.57
     códigos
    0.57
     ఫ
    0.57
    ించు
    0.57
    0.56
    社会的
    0.56
     TextAppearance
    0.56
    🍏
    0.56
    シャフト
    0.56
    Act Density 0.168%

    No Known Activations