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

    Neuronpedia

    INDEX
    Explanations

    state changes and machines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िकुलम
    0.41
     मीट
    0.39
    ूले
    0.39
    ంచ్
    0.38
    补偿
    0.37
     contributo
    0.37
     Ouvrard
    0.37
    侮
    0.37
    伸縮
    0.37
    )[:
    0.36
    POSITIVE LOGITS
    状态
    2.33
     상태
    2.25
     state
    2.23
     estado
    2.23
    状態
    2.14
     состояние
    2.11
     состояния
    2.11
    狀態
    2.11
    state
    2.08
     states
    2.06
    Act Density 0.067%

    No Known Activations