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

    Neuronpedia

    INDEX
    Explanations

    weather radar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鬓
    -0.75
     ברי
    -0.74
    ンテ
    -0.71
    ROCK
    -0.70
     TripAdvisor
    -0.70
    娇
    -0.70
    zeczytaj
    -0.69
    ⊨
    -0.68
     multilingual
    -0.68
     IERC
    -0.67
    POSITIVE LOGITS
     radar
    5.25
     Radar
    4.03
    radar
    3.97
    Radar
    3.61
     rad
    2.72
     RAD
    2.58
     sonar
    2.33
    RAD
    2.27
     рада
    2.11
     rada
    1.97
    Act Density 0.072%

    No Known Activations