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

    Neuronpedia

    INDEX
    Explanations

    equilibrium state or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    姜
    0.42
    均衡
    0.41
    公正
    0.41
    誐
    0.41
    平衡
    0.39
     балан
    0.39
     muita
    0.38
     Firewall
    0.38
    磪
    0.38
     ballet
    0.37
    POSITIVE LOGITS
     состояния
    0.48
     state
    0.44
     price
    0.44
     состояние
    0.44
    狀態
    0.43
     prices
    0.42
    populations
    0.42
    state
    0.42
    reached
    0.41
     shapes
    0.40
    Act Density 0.006%

    No Known Activations